| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 9.992520568436799, | |
| "eval_steps": 500, | |
| "global_step": 3340, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.029917726252804786, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019999557642276714, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05983545250560957, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019998230608242915, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08975317875841436, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019996019015303368, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11967090501121914, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019992923059121106, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.14958863126402394, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019988943013600157, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.17950635751682872, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019984079230861296, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2094240837696335, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019978332141210893, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.2393418100224383, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019971702253102856, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.26925953627524307, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019964190153093613, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.2991772625280479, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019955796505790268, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.32909498878085264, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019946522053791753, | |
| "loss": 0.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.35901271503365745, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019936367617623171, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3889304412864622, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019925334095663167, | |
| "loss": 0.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.418848167539267, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001991342246406448, | |
| "loss": 0.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.4487658937920718, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001990063377666755, | |
| "loss": 0.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.4786836200448766, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019886969164907307, | |
| "loss": 0.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.5086013462976814, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001987242983771306, | |
| "loss": 0.0, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.5385190725504861, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019857017081401548, | |
| "loss": 0.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.5684367988032909, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019840732259563128, | |
| "loss": 0.0, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.5983545250560958, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019823576812941137, | |
| "loss": 0.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.6282722513089005, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019805552259304445, | |
| "loss": 0.0, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.6581899775617053, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019786660193313148, | |
| "loss": 0.0, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.6881077038145101, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019766902286377506, | |
| "loss": 0.0, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.7180254300673149, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001974628028651007, | |
| "loss": 0.0, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.7479431563201197, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019724796018171021, | |
| "loss": 0.0, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.7778608825729244, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001970245138210676, | |
| "loss": 0.0, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.8077786088257293, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001967924835518176, | |
| "loss": 0.0, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.837696335078534, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019655188990203647, | |
| "loss": 0.0, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.8676140613313388, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001963027541574161, | |
| "loss": 0.0, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.8975317875841436, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019604509835938064, | |
| "loss": 0.0, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.9274495138369484, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019577894530313654, | |
| "loss": 0.0, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.9573672400897532, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019550431853565577, | |
| "loss": 0.0, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.9872849663425579, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019522124235359263, | |
| "loss": 0.0, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.0172026925953628, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019492974180113426, | |
| "loss": 0.0, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.0471204188481675, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001946298426677848, | |
| "loss": 0.0, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.0770381451009723, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019432157148608378, | |
| "loss": 0.0, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.106955871353777, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019400495552925886, | |
| "loss": 0.0, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.136873597606582, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019368002280881278, | |
| "loss": 0.0, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.1667913238593868, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019334680207204523, | |
| "loss": 0.0, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.1967090501121915, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019300532279950948, | |
| "loss": 0.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.2266267763649963, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001926556152024043, | |
| "loss": 0.0, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.256544502617801, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019229771021990095, | |
| "loss": 0.0, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.2864622288706058, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019193163951640606, | |
| "loss": 0.0, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.3163799551234106, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019155743547876023, | |
| "loss": 0.0, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.3462976813762153, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001911751312133727, | |
| "loss": 0.0, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.37621540762902, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019078476054329237, | |
| "loss": 0.0, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.406133133881825, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001903863580052154, | |
| "loss": 0.0, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.4360508601346298, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018997995884642967, | |
| "loss": 0.0, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.4659685863874345, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001895655990216966, | |
| "loss": 0.0, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.4958863126402393, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018914331519006986, | |
| "loss": 0.0, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.5258040388930443, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018871314471165232, | |
| "loss": 0.0, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.555721765145849, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018827512564429074, | |
| "loss": 0.0, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.5856394913986538, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018782929674020856, | |
| "loss": 0.0, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.6155572176514585, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018737569744257756, | |
| "loss": 0.0, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.6454749439042633, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018691436788202822, | |
| "loss": 0.0, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.675392670157068, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018644534887309944, | |
| "loss": 0.0, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.7053103964098728, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001859686819106274, | |
| "loss": 0.0, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.7352281226626776, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018548440916607453, | |
| "loss": 0.0, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.7651458489154823, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018499257348379854, | |
| "loss": 0.0, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.795063575168287, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018449321837726208, | |
| "loss": 0.0, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.824981301421092, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018398638802518262, | |
| "loss": 0.0, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.8548990276738968, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018347212726762437, | |
| "loss": 0.0, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.8848167539267016, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018295048160203088, | |
| "loss": 0.0, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.9147344801795063, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018242149717919993, | |
| "loss": 0.0, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.9446522064323113, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018188522079920055, | |
| "loss": 0.0, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.974569932685116, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018134169990723247, | |
| "loss": 0.0, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 2.004487658937921, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018079098258942845, | |
| "loss": 0.0, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 2.0344053851907256, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018023311756860038, | |
| "loss": 0.0, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 2.0643231114435303, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017966815419992829, | |
| "loss": 0.0, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 2.094240837696335, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017909614246659409, | |
| "loss": 0.0, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.12415856394914, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001785171329753594, | |
| "loss": 0.0, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 2.1540762902019446, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017793117695208828, | |
| "loss": 0.0, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.1839940164547493, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001773383262372152, | |
| "loss": 0.0, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 2.213911742707554, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001767386332811587, | |
| "loss": 0.0, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 2.243829468960359, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001761321511396809, | |
| "loss": 0.0, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.273747195213164, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017551893346919362, | |
| "loss": 0.0, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 2.303664921465969, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017489903452201145, | |
| "loss": 0.0, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 2.3335826477187736, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001742725091415517, | |
| "loss": 0.0, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 2.3635003739715783, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017363941275748263, | |
| "loss": 0.0, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 2.393418100224383, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017299980138081922, | |
| "loss": 0.0, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.423335826477188, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017235373159896794, | |
| "loss": 0.0, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 2.4532535527299926, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017170126057072032, | |
| "loss": 0.0, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 2.4831712789827973, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017104244602119613, | |
| "loss": 0.0, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 2.513089005235602, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017037734623673615, | |
| "loss": 0.0, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.543006731488407, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016970602005974568, | |
| "loss": 0.0, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.5729244577412116, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016902852688348866, | |
| "loss": 0.0, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.6028421839940163, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016834492664683274, | |
| "loss": 0.0, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.632759910246821, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016765527982894689, | |
| "loss": 0.0, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.662677636499626, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016695964744395028, | |
| "loss": 0.0, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.6925953627524306, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016625809103551462, | |
| "loss": 0.0, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.7225130890052354, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016555067267141896, | |
| "loss": 0.0, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.75243081525804, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001648374549380587, | |
| "loss": 0.0, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.7823485415108453, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016411850093490837, | |
| "loss": 0.0, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.81226626776365, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016339387426893918, | |
| "loss": 0.0, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.842183994016455, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016266363904899163, | |
| "loss": 0.0, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.8721017202692596, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016192785988010353, | |
| "loss": 0.0, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.9020194465220643, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016118660185779446, | |
| "loss": 0.0, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.931937172774869, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001604399305623067, | |
| "loss": 0.0, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.961854899027674, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015968791205280306, | |
| "loss": 0.0, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.9917726252804786, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015893061286152276, | |
| "loss": 0.0, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.0216903515332834, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015816809998789492, | |
| "loss": 0.0, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 3.051608077786088, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015740044089261138, | |
| "loss": 0.0, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 3.081525804038893, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015662770349165802, | |
| "loss": 0.0, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 3.1114435302916976, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015584995615030634, | |
| "loss": 0.0, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 3.141361256544503, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015506726767706497, | |
| "loss": 0.0, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 3.1712789827973076, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015427970731759212, | |
| "loss": 0.0, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 3.2011967090501123, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015348734474856932, | |
| "loss": 0.0, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 3.231114435302917, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000152690250071537, | |
| "loss": 0.0, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 3.261032161555722, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001518884938066924, | |
| "loss": 0.0, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 3.2909498878085266, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001510821468866508, | |
| "loss": 0.0, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 3.3208676140613314, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001502712806501697, | |
| "loss": 0.0, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 3.350785340314136, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014945596683583754, | |
| "loss": 0.0, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 3.380703066566941, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014863627757572687, | |
| "loss": 0.0, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 3.4106207928197456, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014781228538901267, | |
| "loss": 0.0, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 3.4405385190725504, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014698406317555652, | |
| "loss": 0.0, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 3.470456245325355, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014615168420945688, | |
| "loss": 0.0, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 3.50037397157816, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014531522213256674, | |
| "loss": 0.0, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 3.5302916978309646, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014447475094797797, | |
| "loss": 0.0, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 3.5602094240837694, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014363034501347456, | |
| "loss": 0.0, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 3.590127150336574, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001427820790349539, | |
| "loss": 0.0, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 3.6200448765893793, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001419300280598173, | |
| "loss": 0.0, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 3.649962602842184, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014107426747033075, | |
| "loss": 0.0, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 3.679880329094989, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001402148729769554, | |
| "loss": 0.0, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 3.7097980553477936, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013935192061164956, | |
| "loss": 0.0, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 3.7397157816005984, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013848548672114197, | |
| "loss": 0.0, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 3.769633507853403, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013761564796017724, | |
| "loss": 0.0, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 3.799551234106208, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013674248128473418, | |
| "loss": 0.0, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 3.8294689603590126, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001358660639452173, | |
| "loss": 0.0, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 3.8593866866118174, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001349864734796224, | |
| "loss": 0.0, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 3.889304412864622, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001341037877066766, | |
| "loss": 0.0, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 3.9192221391174273, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013321808471895375, | |
| "loss": 0.0, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 3.949139865370232, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013232944287596522, | |
| "loss": 0.0, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 3.979057591623037, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013143794079722754, | |
| "loss": 0.0, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 4.008975317875842, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013054365735530664, | |
| "loss": 0.0, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 4.038893044128646, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012964667166884004, | |
| "loss": 0.0, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 4.068810770381451, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012874706309553698, | |
| "loss": 0.0, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 4.098728496634256, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012784491122515743, | |
| "loss": 0.0, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 4.128646222887061, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012694029587247095, | |
| "loss": 0.0, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 4.158563949139865, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012603329707019508, | |
| "loss": 0.0, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 4.18848167539267, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001251239950619149, | |
| "loss": 0.0, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 4.218399401645475, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001242124702949836, | |
| "loss": 0.0, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 4.24831712789828, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001232988034134053, | |
| "loss": 0.0, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 4.278234854151084, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012238307525070042, | |
| "loss": 0.0, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 4.308152580403889, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012146536682275387, | |
| "loss": 0.0, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 4.338070306656694, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012054575932064787, | |
| "loss": 0.0, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 4.367988032909499, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001196243341034786, | |
| "loss": 0.0, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 4.397905759162303, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011870117269115833, | |
| "loss": 0.0, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 4.427823485415108, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011777635675720313, | |
| "loss": 0.0, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 4.457741211667913, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011684996812150726, | |
| "loss": 0.0, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 4.487658937920718, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011592208874310426, | |
| "loss": 0.0, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.517576664173522, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011499280071291596, | |
| "loss": 0.0, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 4.547494390426328, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011406218624648985, | |
| "loss": 0.0, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 4.577412116679133, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011313032767672524, | |
| "loss": 0.0, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 4.607329842931938, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011219730744658921, | |
| "loss": 0.0, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 4.637247569184742, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011126320810182272, | |
| "loss": 0.0, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 4.667165295437547, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011032811228363766, | |
| "loss": 0.0, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 4.697083021690352, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010939210272140545, | |
| "loss": 0.0, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 4.727000747943157, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010845526222533791, | |
| "loss": 0.0, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 4.756918474195961, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010751767367916082, | |
| "loss": 0.0, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 4.786836200448766, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010657942003278107, | |
| "loss": 0.0, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 4.816753926701571, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010564058429494808, | |
| "loss": 0.0, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 4.846671652954376, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010470124952590977, | |
| "loss": 0.0, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 4.87658937920718, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010376149883006406, | |
| "loss": 0.0, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 4.906507105459985, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001028214153486066, | |
| "loss": 0.0, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 4.93642483171279, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010188108225217516, | |
| "loss": 0.0, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 4.966342557965595, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010094058273349125, | |
| "loss": 0.0, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 4.996260284218399, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 5.026178010471204, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.90594172665088e-05, | |
| "loss": 0.0, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 5.056095736724009, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.811891774782484e-05, | |
| "loss": 0.0, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 5.086013462976814, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.717858465139342e-05, | |
| "loss": 0.0, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 5.115931189229618, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.623850116993596e-05, | |
| "loss": 0.0, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 5.145848915482423, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.529875047409027e-05, | |
| "loss": 0.0, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 5.175766641735228, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.43594157050519e-05, | |
| "loss": 0.0, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 5.205684367988033, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.342057996721894e-05, | |
| "loss": 0.0, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 5.2356020942408374, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.248232632083923e-05, | |
| "loss": 0.0, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 5.265519820493642, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.15447377746621e-05, | |
| "loss": 0.0, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 5.295437546746447, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.060789727859457e-05, | |
| "loss": 0.0, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 5.325355272999252, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.967188771636236e-05, | |
| "loss": 0.0, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 5.3552729992520565, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.873679189817732e-05, | |
| "loss": 0.0, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 5.385190725504861, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.78026925534108e-05, | |
| "loss": 0.0, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 5.415108451757666, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.686967232327478e-05, | |
| "loss": 0.0, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 5.445026178010472, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.59378137535102e-05, | |
| "loss": 0.0, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 5.474943904263276, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.500719928708405e-05, | |
| "loss": 0.0, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 5.504861630516081, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.407791125689578e-05, | |
| "loss": 0.0, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 5.534779356768886, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.315003187849277e-05, | |
| "loss": 0.0, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 5.564697083021691, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.222364324279689e-05, | |
| "loss": 0.0, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 5.594614809274495, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.129882730884168e-05, | |
| "loss": 0.0, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 5.6245325355273, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.037566589652141e-05, | |
| "loss": 0.0, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 5.654450261780105, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.945424067935217e-05, | |
| "loss": 0.0, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 5.68436798803291, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.853463317724614e-05, | |
| "loss": 0.0, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 5.714285714285714, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.761692474929961e-05, | |
| "loss": 0.0, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 5.744203440538519, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.67011965865947e-05, | |
| "loss": 0.0, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 5.774121166791324, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.578752970501642e-05, | |
| "loss": 0.0, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 5.804038893044129, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.487600493808513e-05, | |
| "loss": 0.0, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 5.833956619296933, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.396670292980492e-05, | |
| "loss": 0.0, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 5.863874345549738, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.305970412752909e-05, | |
| "loss": 0.0, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 5.893792071802543, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.215508877484258e-05, | |
| "loss": 0.0, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 5.923709798055348, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.125293690446306e-05, | |
| "loss": 0.0, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 5.9536275243081525, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.035332833115997e-05, | |
| "loss": 0.0, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 5.983545250560957, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.945634264469339e-05, | |
| "loss": 0.0, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 6.013462976813762, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.85620592027725e-05, | |
| "loss": 0.0, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 6.043380703066567, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.76705571240348e-05, | |
| "loss": 0.0, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 6.0732984293193715, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.678191528104629e-05, | |
| "loss": 0.0, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 6.103216155572176, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.58962122933234e-05, | |
| "loss": 0.0, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 6.133133881824981, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.501352652037764e-05, | |
| "loss": 0.0, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 6.163051608077786, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.413393605478275e-05, | |
| "loss": 0.0, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 6.1929693343305905, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.325751871526588e-05, | |
| "loss": 0.0, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 6.222887060583395, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.238435203982278e-05, | |
| "loss": 0.0, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 6.252804786836201, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.151451327885805e-05, | |
| "loss": 0.0, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 6.282722513089006, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.0648079388350466e-05, | |
| "loss": 0.0, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 6.31264023934181, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.978512702304461e-05, | |
| "loss": 0.0, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 6.342557965594615, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.892573252966926e-05, | |
| "loss": 0.0, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 6.37247569184742, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.806997194018271e-05, | |
| "loss": 0.0, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 6.402393418100225, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.721792096504611e-05, | |
| "loss": 0.0, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 6.432311144353029, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.636965498652544e-05, | |
| "loss": 0.0, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 6.462228870605834, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.5525249052022076e-05, | |
| "loss": 0.0, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 6.492146596858639, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.4684777867433335e-05, | |
| "loss": 0.0, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 6.522064323111444, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.3848315790543126e-05, | |
| "loss": 0.0, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 6.551982049364248, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.301593682444352e-05, | |
| "loss": 0.0, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 6.581899775617053, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.218771461098733e-05, | |
| "loss": 0.0, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 6.611817501869858, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.1363722424273156e-05, | |
| "loss": 0.0, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 6.641735228122663, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.054403316416247e-05, | |
| "loss": 0.0, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 6.6716529543754675, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.972871934983032e-05, | |
| "loss": 0.0, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 6.701570680628272, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.891785311334923e-05, | |
| "loss": 0.0, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 6.731488406881077, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.811150619330759e-05, | |
| "loss": 0.0, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 6.761406133133882, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.7309749928463035e-05, | |
| "loss": 0.0, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 6.7913238593866865, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6512655251430695e-05, | |
| "loss": 0.0, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 6.821241585639491, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5720292682407874e-05, | |
| "loss": 0.0, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 6.851159311892296, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.493273232293506e-05, | |
| "loss": 0.0, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 6.881077038145101, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.41500438496937e-05, | |
| "loss": 0.0, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 6.9109947643979055, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.3372296508342026e-05, | |
| "loss": 0.0, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 6.94091249065071, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2599559107388645e-05, | |
| "loss": 0.0, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 6.970830216903515, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.1831900012105105e-05, | |
| "loss": 0.0, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 7.00074794315632, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.10693871384773e-05, | |
| "loss": 0.0, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 7.0306656694091245, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.031208794719695e-05, | |
| "loss": 0.0, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 7.060583395661929, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.95600694376933e-05, | |
| "loss": 0.0, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 7.090501121914735, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.881339814220555e-05, | |
| "loss": 0.0, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 7.12041884816754, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8072140119896504e-05, | |
| "loss": 0.0, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 7.150336574420344, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.733636095100838e-05, | |
| "loss": 0.0, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 7.180254300673149, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.660612573106081e-05, | |
| "loss": 0.0, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 7.210172026925954, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.588149906509166e-05, | |
| "loss": 0.0, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 7.240089753178759, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5162545061941335e-05, | |
| "loss": 0.0, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 7.2700074794315634, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.444932732858107e-05, | |
| "loss": 0.0, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 7.299925205684368, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3741908964485414e-05, | |
| "loss": 0.0, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 7.329842931937173, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.304035255604974e-05, | |
| "loss": 0.0, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 7.359760658189978, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.234472017105313e-05, | |
| "loss": 0.0, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 7.3896783844427825, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.1655073353167285e-05, | |
| "loss": 0.0, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 7.419596110695587, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0971473116511394e-05, | |
| "loss": 0.0, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 7.449513836948392, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0293979940254314e-05, | |
| "loss": 0.0, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 7.479431563201197, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9622653763263874e-05, | |
| "loss": 0.0, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 7.5093492894540015, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8957553978803898e-05, | |
| "loss": 0.0, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 7.539267015706806, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8298739429279707e-05, | |
| "loss": 0.0, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 7.569184741959611, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.764626840103208e-05, | |
| "loss": 0.0, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 7.599102468212416, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7000198619180794e-05, | |
| "loss": 0.0, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 7.6290201944652205, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.636058724251739e-05, | |
| "loss": 0.0, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 7.658937920718025, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5727490858448288e-05, | |
| "loss": 0.0, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 7.68885564697083, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.510096547798857e-05, | |
| "loss": 0.0, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 7.718773373223635, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4481066530806395e-05, | |
| "loss": 0.0, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 7.7486910994764395, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3867848860319144e-05, | |
| "loss": 0.0, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 7.778608825729244, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3261366718841305e-05, | |
| "loss": 0.0, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 7.808526551982049, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2661673762784807e-05, | |
| "loss": 0.0, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 7.838444278234854, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.206882304791176e-05, | |
| "loss": 0.0, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 7.868362004487659, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.148286702464063e-05, | |
| "loss": 0.0, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 7.898279730740464, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0903857533405958e-05, | |
| "loss": 0.0, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 7.928197456993269, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.033184580007177e-05, | |
| "loss": 0.0, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 7.958115183246074, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9766882431399646e-05, | |
| "loss": 0.0, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 7.9880329094988785, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.920901741057153e-05, | |
| "loss": 0.0, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 8.017950635751683, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8658300092767544e-05, | |
| "loss": 0.0, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 8.047868362004488, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8114779200799437e-05, | |
| "loss": 0.0, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 8.077786088257293, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7578502820800045e-05, | |
| "loss": 0.0, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 8.107703814510097, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7049518397969132e-05, | |
| "loss": 0.0, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 8.137621540762902, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.652787273237565e-05, | |
| "loss": 0.0, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 8.167539267015707, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.601361197481741e-05, | |
| "loss": 0.0, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 8.197456993268512, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5506781622737942e-05, | |
| "loss": 0.0, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 8.227374719521316, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.500742651620145e-05, | |
| "loss": 0.0, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 8.257292445774121, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4515590833925507e-05, | |
| "loss": 0.0, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 8.287210172026926, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4031318089372615e-05, | |
| "loss": 0.0, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 8.31712789827973, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3554651126900564e-05, | |
| "loss": 0.0, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 8.347045624532536, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.308563211797179e-05, | |
| "loss": 0.0, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 8.37696335078534, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2624302557422473e-05, | |
| "loss": 0.0, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 8.406881077038145, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2170703259791471e-05, | |
| "loss": 0.0, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 8.43679880329095, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.172487435570926e-05, | |
| "loss": 0.0, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 8.466716529543755, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1286855288347675e-05, | |
| "loss": 0.0, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 8.49663425579656, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0856684809930151e-05, | |
| "loss": 0.0, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 8.526551982049364, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0434400978303426e-05, | |
| "loss": 0.0, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 8.556469708302169, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0020041153570347e-05, | |
| "loss": 0.0, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 8.586387434554974, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.613641994784651e-06, | |
| "loss": 0.0, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 8.616305160807778, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.215239456707635e-06, | |
| "loss": 0.0, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 8.646222887060583, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.824868786627304e-06, | |
| "loss": 0.0, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 8.676140613313388, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.442564521239782e-06, | |
| "loss": 0.0, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 8.706058339566193, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.06836048359394e-06, | |
| "loss": 0.0, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 8.735976065818997, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.70228978009907e-06, | |
| "loss": 0.0, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 8.765893792071802, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.344384797595716e-06, | |
| "loss": 0.0, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 8.795811518324607, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.994677200490507e-06, | |
| "loss": 0.0, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 8.825729244577412, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.653197927954791e-06, | |
| "loss": 0.0, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 8.855646970830216, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.319977191187232e-06, | |
| "loss": 0.0, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 8.885564697083021, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.995044470741151e-06, | |
| "loss": 0.0, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 8.915482423335826, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.678428513916212e-06, | |
| "loss": 0.0, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 8.94540014958863, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.370157332215209e-06, | |
| "loss": 0.0, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 8.975317875841435, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.07025819886574e-06, | |
| "loss": 0.0, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 9.00523560209424, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.778757646407362e-06, | |
| "loss": 0.0, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 9.035153328347045, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.495681464344259e-06, | |
| "loss": 0.0, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 9.06507105459985, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.22105469686348e-06, | |
| "loss": 0.0, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 9.094988780852654, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.954901640619368e-06, | |
| "loss": 0.0, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 9.12490650710546, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6972458425838962e-06, | |
| "loss": 0.0, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 9.154824233358266, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4481100979635306e-06, | |
| "loss": 0.0, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 9.18474195961107, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.207516448182435e-06, | |
| "loss": 0.0, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 9.214659685863875, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9754861789324073e-06, | |
| "loss": 0.0, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 9.24457741211668, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.752039818289809e-06, | |
| "loss": 0.0, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 9.274495138369485, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.537197134899294e-06, | |
| "loss": 0.0, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 9.30441286462229, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.330977136224932e-06, | |
| "loss": 0.0, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 9.334330590875094, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1333980668685414e-06, | |
| "loss": 0.0, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 9.364248317127899, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9444774069555694e-06, | |
| "loss": 0.0, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 9.394166043380704, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7642318705886286e-06, | |
| "loss": 0.0, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 9.424083769633508, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5926774043687365e-06, | |
| "loss": 0.0, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 9.454001495886313, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4298291859845214e-06, | |
| "loss": 0.0, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 9.483919222139118, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2757016228693964e-06, | |
| "loss": 0.0, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 9.513836948391923, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1303083509269452e-06, | |
| "loss": 0.0, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 9.543754674644727, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.936622333245104e-07, | |
| "loss": 0.0, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 9.573672400897532, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.657753593552143e-07, | |
| "loss": 0.0, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 9.603590127150337, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.466590433683251e-07, | |
| "loss": 0.0, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 9.633507853403142, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.363238237683033e-07, | |
| "loss": 0.0, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 9.663425579655947, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.347794620824576e-07, | |
| "loss": 0.0, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 9.693343305908751, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.4203494209733576e-07, | |
| "loss": 0.0, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 9.723261032161556, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.580984690638611e-07, | |
| "loss": 0.0, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 9.75317875841436, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8297746897146816e-07, | |
| "loss": 0.0, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 9.783096484667166, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1667858789105043e-07, | |
| "loss": 0.0, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 9.81301421091997, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5920769138706438e-07, | |
| "loss": 0.0, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 9.842931937172775, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1056986399845537e-07, | |
| "loss": 0.0, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 9.87284966342558, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.07694087889621e-08, | |
| "loss": 0.0, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 9.902767389678385, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.980984696634327e-08, | |
| "loss": 0.0, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 9.93268511593119, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7693917570837936e-08, | |
| "loss": 0.0, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 9.962602842183994, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.42357723288156e-09, | |
| "loss": 0.0, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 9.992520568436799, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 9.992520568436799, | |
| "step": 3340, | |
| "total_flos": 1.6429048267800576e+17, | |
| "train_loss": 0.0, | |
| "train_runtime": 3248.6622, | |
| "train_samples_per_second": 4.116, | |
| "train_steps_per_second": 1.028 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 3340, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 1.6429048267800576e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |