| { | |
| "best_global_step": 11600, | |
| "best_metric": 2.4339404106140137, | |
| "best_model_checkpoint": "/kaggle/working/senko_adaptive/checkpoint-11600", | |
| "epoch": 2.936886750648857, | |
| "eval_steps": 200, | |
| "global_step": 11600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0126606317655251, | |
| "grad_norm": 0.4365496337413788, | |
| "learning_rate": 2.067510548523207e-06, | |
| "loss": 3.4408, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0253212635310502, | |
| "grad_norm": 0.5391681790351868, | |
| "learning_rate": 4.177215189873418e-06, | |
| "loss": 3.4568, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0379818952965753, | |
| "grad_norm": 0.7692704796791077, | |
| "learning_rate": 6.28691983122363e-06, | |
| "loss": 3.4686, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0506425270621004, | |
| "grad_norm": 0.9071826934814453, | |
| "learning_rate": 8.39662447257384e-06, | |
| "loss": 3.5075, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.0506425270621004, | |
| "eval_loss": 3.5223069190979004, | |
| "eval_runtime": 41.5235, | |
| "eval_samples_per_second": 42.289, | |
| "eval_steps_per_second": 42.289, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.0633031588276255, | |
| "grad_norm": 0.976381778717041, | |
| "learning_rate": 1.0506329113924052e-05, | |
| "loss": 3.3576, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.0759637905931506, | |
| "grad_norm": 0.81010901927948, | |
| "learning_rate": 1.2616033755274262e-05, | |
| "loss": 3.3492, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.0886244223586757, | |
| "grad_norm": 0.9288440942764282, | |
| "learning_rate": 1.4725738396624473e-05, | |
| "loss": 3.2229, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.1012850541242008, | |
| "grad_norm": 1.110400676727295, | |
| "learning_rate": 1.6835443037974685e-05, | |
| "loss": 3.1555, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.1012850541242008, | |
| "eval_loss": 3.1509861946105957, | |
| "eval_runtime": 40.9241, | |
| "eval_samples_per_second": 42.909, | |
| "eval_steps_per_second": 42.909, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.1139456858897259, | |
| "grad_norm": 1.4328745603561401, | |
| "learning_rate": 1.8945147679324897e-05, | |
| "loss": 3.0152, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.126606317655251, | |
| "grad_norm": 1.094860553741455, | |
| "learning_rate": 2.1054852320675106e-05, | |
| "loss": 3.0463, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.1392669494207761, | |
| "grad_norm": 1.5432164669036865, | |
| "learning_rate": 2.3164556962025318e-05, | |
| "loss": 2.9119, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.1519275811863012, | |
| "grad_norm": 1.2089171409606934, | |
| "learning_rate": 2.5274261603375527e-05, | |
| "loss": 2.885, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.1519275811863012, | |
| "eval_loss": 2.7955658435821533, | |
| "eval_runtime": 41.2266, | |
| "eval_samples_per_second": 42.594, | |
| "eval_steps_per_second": 42.594, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.1645882129518263, | |
| "grad_norm": 1.0353807210922241, | |
| "learning_rate": 2.738396624472574e-05, | |
| "loss": 2.8395, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.1772488447173514, | |
| "grad_norm": 1.6014362573623657, | |
| "learning_rate": 2.949367088607595e-05, | |
| "loss": 2.8229, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.18990947648287648, | |
| "grad_norm": 1.0306800603866577, | |
| "learning_rate": 3.160337552742616e-05, | |
| "loss": 2.9251, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.2025701082484016, | |
| "grad_norm": 1.7377468347549438, | |
| "learning_rate": 3.3713080168776376e-05, | |
| "loss": 2.816, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.2025701082484016, | |
| "eval_loss": 2.6652894020080566, | |
| "eval_runtime": 41.6497, | |
| "eval_samples_per_second": 42.161, | |
| "eval_steps_per_second": 42.161, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.2152307400139267, | |
| "grad_norm": 1.550484299659729, | |
| "learning_rate": 3.5822784810126585e-05, | |
| "loss": 2.8018, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.2278913717794518, | |
| "grad_norm": 1.1680374145507812, | |
| "learning_rate": 3.7932489451476794e-05, | |
| "loss": 2.8037, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.24055200354497688, | |
| "grad_norm": 1.4538466930389404, | |
| "learning_rate": 4.004219409282701e-05, | |
| "loss": 2.7734, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.253212635310502, | |
| "grad_norm": 1.5268754959106445, | |
| "learning_rate": 4.215189873417722e-05, | |
| "loss": 2.7975, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.253212635310502, | |
| "eval_loss": 2.6034388542175293, | |
| "eval_runtime": 41.1034, | |
| "eval_samples_per_second": 42.722, | |
| "eval_steps_per_second": 42.722, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.2658732670760271, | |
| "grad_norm": 1.813955545425415, | |
| "learning_rate": 4.426160337552743e-05, | |
| "loss": 2.7258, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.2785338988415522, | |
| "grad_norm": 1.664474368095398, | |
| "learning_rate": 4.637130801687764e-05, | |
| "loss": 2.7607, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.2911945306070773, | |
| "grad_norm": 2.343366861343384, | |
| "learning_rate": 4.8481012658227845e-05, | |
| "loss": 2.7418, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.3038551623726024, | |
| "grad_norm": 1.5289666652679443, | |
| "learning_rate": 4.993434627649597e-05, | |
| "loss": 2.7779, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.3038551623726024, | |
| "eval_loss": 2.571211814880371, | |
| "eval_runtime": 41.5835, | |
| "eval_samples_per_second": 42.228, | |
| "eval_steps_per_second": 42.228, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.31651579413812747, | |
| "grad_norm": 1.2860196828842163, | |
| "learning_rate": 4.969986869255299e-05, | |
| "loss": 2.7216, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.3291764259036526, | |
| "grad_norm": 1.2128461599349976, | |
| "learning_rate": 4.946539110861002e-05, | |
| "loss": 2.6822, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.3418370576691777, | |
| "grad_norm": 0.8949031233787537, | |
| "learning_rate": 4.9230913524667046e-05, | |
| "loss": 2.696, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.3544976894347028, | |
| "grad_norm": 1.1098757982254028, | |
| "learning_rate": 4.900112549240293e-05, | |
| "loss": 2.7004, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.3544976894347028, | |
| "eval_loss": 2.5462076663970947, | |
| "eval_runtime": 41.8547, | |
| "eval_samples_per_second": 41.955, | |
| "eval_steps_per_second": 41.955, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.3671583212002279, | |
| "grad_norm": 1.3600550889968872, | |
| "learning_rate": 4.8766647908459956e-05, | |
| "loss": 2.6385, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.37981895296575297, | |
| "grad_norm": 1.1471352577209473, | |
| "learning_rate": 4.853217032451698e-05, | |
| "loss": 2.7002, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.3924795847312781, | |
| "grad_norm": 1.666717767715454, | |
| "learning_rate": 4.8297692740574e-05, | |
| "loss": 2.6755, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.4051402164968032, | |
| "grad_norm": 1.4194293022155762, | |
| "learning_rate": 4.8063215156631034e-05, | |
| "loss": 2.6852, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.4051402164968032, | |
| "eval_loss": 2.5299158096313477, | |
| "eval_runtime": 41.8943, | |
| "eval_samples_per_second": 41.915, | |
| "eval_steps_per_second": 41.915, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.4178008482623283, | |
| "grad_norm": 0.9786908626556396, | |
| "learning_rate": 4.7828737572688055e-05, | |
| "loss": 2.7279, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.4304614800278534, | |
| "grad_norm": 1.1531881093978882, | |
| "learning_rate": 4.759425998874508e-05, | |
| "loss": 2.6643, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.4431221117933785, | |
| "grad_norm": 1.1486274003982544, | |
| "learning_rate": 4.7359782404802105e-05, | |
| "loss": 2.6994, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.4557827435589036, | |
| "grad_norm": 1.2005631923675537, | |
| "learning_rate": 4.7125304820859126e-05, | |
| "loss": 2.7233, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.4557827435589036, | |
| "eval_loss": 2.520224094390869, | |
| "eval_runtime": 41.9149, | |
| "eval_samples_per_second": 41.894, | |
| "eval_steps_per_second": 41.894, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.4684433753244287, | |
| "grad_norm": 1.2023993730545044, | |
| "learning_rate": 4.6890827236916154e-05, | |
| "loss": 2.6352, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.48110400708995377, | |
| "grad_norm": 1.5334537029266357, | |
| "learning_rate": 4.665634965297318e-05, | |
| "loss": 2.6827, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.4937646388554789, | |
| "grad_norm": 1.9828767776489258, | |
| "learning_rate": 4.6421872069030204e-05, | |
| "loss": 2.6507, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.506425270621004, | |
| "grad_norm": 1.5031970739364624, | |
| "learning_rate": 4.6187394485087225e-05, | |
| "loss": 2.6432, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.506425270621004, | |
| "eval_loss": 2.511120319366455, | |
| "eval_runtime": 41.0032, | |
| "eval_samples_per_second": 42.826, | |
| "eval_steps_per_second": 42.826, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.5190859023865291, | |
| "grad_norm": 1.2630196809768677, | |
| "learning_rate": 4.5952916901144253e-05, | |
| "loss": 2.6226, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.5317465341520542, | |
| "grad_norm": 1.3230444192886353, | |
| "learning_rate": 4.5718439317201275e-05, | |
| "loss": 2.6596, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.5444071659175793, | |
| "grad_norm": 1.2275980710983276, | |
| "learning_rate": 4.54839617332583e-05, | |
| "loss": 2.6419, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.5570677976831044, | |
| "grad_norm": 1.2460874319076538, | |
| "learning_rate": 4.524948414931533e-05, | |
| "loss": 2.6432, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.5570677976831044, | |
| "eval_loss": 2.5041472911834717, | |
| "eval_runtime": 40.9893, | |
| "eval_samples_per_second": 42.84, | |
| "eval_steps_per_second": 42.84, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.5697284294486294, | |
| "grad_norm": 1.4000052213668823, | |
| "learning_rate": 4.501500656537235e-05, | |
| "loss": 2.681, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.5823890612141546, | |
| "grad_norm": 1.139631748199463, | |
| "learning_rate": 4.4780528981429374e-05, | |
| "loss": 2.6119, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.5950496929796797, | |
| "grad_norm": 1.4779937267303467, | |
| "learning_rate": 4.45460513974864e-05, | |
| "loss": 2.615, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.6077103247452048, | |
| "grad_norm": 1.0678008794784546, | |
| "learning_rate": 4.431157381354343e-05, | |
| "loss": 2.6014, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.6077103247452048, | |
| "eval_loss": 2.4982025623321533, | |
| "eval_runtime": 41.0253, | |
| "eval_samples_per_second": 42.803, | |
| "eval_steps_per_second": 42.803, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.6203709565107299, | |
| "grad_norm": 1.4893417358398438, | |
| "learning_rate": 4.407709622960045e-05, | |
| "loss": 2.574, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.6330315882762549, | |
| "grad_norm": 1.3910084962844849, | |
| "learning_rate": 4.384261864565748e-05, | |
| "loss": 2.6452, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.6456922200417801, | |
| "grad_norm": 2.1891777515411377, | |
| "learning_rate": 4.36081410617145e-05, | |
| "loss": 2.6627, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.6583528518073052, | |
| "grad_norm": 1.6157493591308594, | |
| "learning_rate": 4.337366347777152e-05, | |
| "loss": 2.6508, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.6583528518073052, | |
| "eval_loss": 2.4939932823181152, | |
| "eval_runtime": 41.1171, | |
| "eval_samples_per_second": 42.707, | |
| "eval_steps_per_second": 42.707, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.6710134835728303, | |
| "grad_norm": 1.2457774877548218, | |
| "learning_rate": 4.313918589382856e-05, | |
| "loss": 2.6282, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 0.6836741153383554, | |
| "grad_norm": 2.1914823055267334, | |
| "learning_rate": 4.290470830988558e-05, | |
| "loss": 2.6931, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.6963347471038804, | |
| "grad_norm": 1.186735987663269, | |
| "learning_rate": 4.26702307259426e-05, | |
| "loss": 2.6229, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 0.7089953788694056, | |
| "grad_norm": 1.868569016456604, | |
| "learning_rate": 4.243575314199963e-05, | |
| "loss": 2.6312, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.7089953788694056, | |
| "eval_loss": 2.487884283065796, | |
| "eval_runtime": 41.4603, | |
| "eval_samples_per_second": 42.354, | |
| "eval_steps_per_second": 42.354, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.7216560106349307, | |
| "grad_norm": 1.3528209924697876, | |
| "learning_rate": 4.220127555805665e-05, | |
| "loss": 2.5675, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 0.7343166424004558, | |
| "grad_norm": 1.319753646850586, | |
| "learning_rate": 4.196679797411368e-05, | |
| "loss": 2.5599, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.7469772741659809, | |
| "grad_norm": 1.338115930557251, | |
| "learning_rate": 4.1732320390170706e-05, | |
| "loss": 2.6528, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 0.7596379059315059, | |
| "grad_norm": 1.2844877243041992, | |
| "learning_rate": 4.149784280622773e-05, | |
| "loss": 2.698, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.7596379059315059, | |
| "eval_loss": 2.4847159385681152, | |
| "eval_runtime": 41.1324, | |
| "eval_samples_per_second": 42.691, | |
| "eval_steps_per_second": 42.691, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.772298537697031, | |
| "grad_norm": 1.4525926113128662, | |
| "learning_rate": 4.126336522228475e-05, | |
| "loss": 2.622, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 0.7849591694625562, | |
| "grad_norm": 1.5551460981369019, | |
| "learning_rate": 4.102888763834178e-05, | |
| "loss": 2.6219, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.7976198012280813, | |
| "grad_norm": 1.39869225025177, | |
| "learning_rate": 4.0794410054398805e-05, | |
| "loss": 2.5807, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 0.8102804329936064, | |
| "grad_norm": 1.4835882186889648, | |
| "learning_rate": 4.0559932470455826e-05, | |
| "loss": 2.6733, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.8102804329936064, | |
| "eval_loss": 2.4816081523895264, | |
| "eval_runtime": 40.9609, | |
| "eval_samples_per_second": 42.87, | |
| "eval_steps_per_second": 42.87, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.8229410647591315, | |
| "grad_norm": 1.2404175996780396, | |
| "learning_rate": 4.0325454886512854e-05, | |
| "loss": 2.6991, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 0.8356016965246565, | |
| "grad_norm": 1.3770995140075684, | |
| "learning_rate": 4.0090977302569876e-05, | |
| "loss": 2.5512, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.8482623282901817, | |
| "grad_norm": 1.1706722974777222, | |
| "learning_rate": 3.98564997186269e-05, | |
| "loss": 2.6126, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 0.8609229600557068, | |
| "grad_norm": 1.290719985961914, | |
| "learning_rate": 3.9622022134683925e-05, | |
| "loss": 2.6178, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.8609229600557068, | |
| "eval_loss": 2.4776341915130615, | |
| "eval_runtime": 41.0702, | |
| "eval_samples_per_second": 42.756, | |
| "eval_steps_per_second": 42.756, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.8735835918212319, | |
| "grad_norm": 1.32352614402771, | |
| "learning_rate": 3.938754455074095e-05, | |
| "loss": 2.5755, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 0.886244223586757, | |
| "grad_norm": 1.4078598022460938, | |
| "learning_rate": 3.9153066966797975e-05, | |
| "loss": 2.6678, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.898904855352282, | |
| "grad_norm": 1.1207985877990723, | |
| "learning_rate": 3.8918589382855e-05, | |
| "loss": 2.5674, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 0.9115654871178072, | |
| "grad_norm": 1.4133316278457642, | |
| "learning_rate": 3.8684111798912024e-05, | |
| "loss": 2.5949, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.9115654871178072, | |
| "eval_loss": 2.473680019378662, | |
| "eval_runtime": 42.1618, | |
| "eval_samples_per_second": 41.649, | |
| "eval_steps_per_second": 41.649, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.9242261188833323, | |
| "grad_norm": 0.9091076254844666, | |
| "learning_rate": 3.844963421496905e-05, | |
| "loss": 2.6154, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 0.9368867506488574, | |
| "grad_norm": 1.3824701309204102, | |
| "learning_rate": 3.821515663102608e-05, | |
| "loss": 2.6569, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.9495473824143825, | |
| "grad_norm": 1.3944271802902222, | |
| "learning_rate": 3.79806790470831e-05, | |
| "loss": 2.5874, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 0.9622080141799075, | |
| "grad_norm": 1.504271388053894, | |
| "learning_rate": 3.774620146314012e-05, | |
| "loss": 2.6422, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.9622080141799075, | |
| "eval_loss": 2.4708938598632812, | |
| "eval_runtime": 41.7484, | |
| "eval_samples_per_second": 42.061, | |
| "eval_steps_per_second": 42.061, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.9748686459454327, | |
| "grad_norm": 1.1897855997085571, | |
| "learning_rate": 3.751172387919715e-05, | |
| "loss": 2.6979, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 0.9875292777109578, | |
| "grad_norm": 0.9344286918640137, | |
| "learning_rate": 3.727724629525417e-05, | |
| "loss": 2.6678, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 4.620224475860596, | |
| "learning_rate": 3.70427687113112e-05, | |
| "loss": 2.5652, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 1.0126606317655251, | |
| "grad_norm": 1.275289535522461, | |
| "learning_rate": 3.680829112736823e-05, | |
| "loss": 2.5655, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.0126606317655251, | |
| "eval_loss": 2.4711084365844727, | |
| "eval_runtime": 40.8651, | |
| "eval_samples_per_second": 42.971, | |
| "eval_steps_per_second": 42.971, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.0253212635310502, | |
| "grad_norm": 1.460325837135315, | |
| "learning_rate": 3.657381354342525e-05, | |
| "loss": 2.627, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 1.0379818952965754, | |
| "grad_norm": 1.2776564359664917, | |
| "learning_rate": 3.633933595948227e-05, | |
| "loss": 2.626, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 1.0506425270621005, | |
| "grad_norm": 1.5591661930084229, | |
| "learning_rate": 3.6109547927218154e-05, | |
| "loss": 2.6603, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 1.0633031588276256, | |
| "grad_norm": 1.0031243562698364, | |
| "learning_rate": 3.587507034327519e-05, | |
| "loss": 2.5955, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 1.0633031588276256, | |
| "eval_loss": 2.4686498641967773, | |
| "eval_runtime": 41.059, | |
| "eval_samples_per_second": 42.768, | |
| "eval_steps_per_second": 42.768, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 1.0759637905931505, | |
| "grad_norm": 1.662988543510437, | |
| "learning_rate": 3.564059275933221e-05, | |
| "loss": 2.5906, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 1.0886244223586756, | |
| "grad_norm": 1.5336205959320068, | |
| "learning_rate": 3.540611517538923e-05, | |
| "loss": 2.62, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 1.1012850541242007, | |
| "grad_norm": 1.2656798362731934, | |
| "learning_rate": 3.517163759144626e-05, | |
| "loss": 2.6229, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 1.1139456858897259, | |
| "grad_norm": 1.5082098245620728, | |
| "learning_rate": 3.493716000750328e-05, | |
| "loss": 2.6015, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 1.1139456858897259, | |
| "eval_loss": 2.466660737991333, | |
| "eval_runtime": 40.8118, | |
| "eval_samples_per_second": 43.027, | |
| "eval_steps_per_second": 43.027, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 1.126606317655251, | |
| "grad_norm": 1.8201966285705566, | |
| "learning_rate": 3.470268242356031e-05, | |
| "loss": 2.6495, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 1.139266949420776, | |
| "grad_norm": 1.3035717010498047, | |
| "learning_rate": 3.446820483961734e-05, | |
| "loss": 2.531, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.1519275811863012, | |
| "grad_norm": 1.2087314128875732, | |
| "learning_rate": 3.423372725567436e-05, | |
| "loss": 2.5412, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 1.1645882129518264, | |
| "grad_norm": 1.2561825513839722, | |
| "learning_rate": 3.399924967173139e-05, | |
| "loss": 2.6465, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 1.1645882129518264, | |
| "eval_loss": 2.4628918170928955, | |
| "eval_runtime": 40.8309, | |
| "eval_samples_per_second": 43.007, | |
| "eval_steps_per_second": 43.007, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 1.1772488447173515, | |
| "grad_norm": 1.7700440883636475, | |
| "learning_rate": 3.376477208778841e-05, | |
| "loss": 2.5658, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 1.1899094764828764, | |
| "grad_norm": 1.4953458309173584, | |
| "learning_rate": 3.3530294503845436e-05, | |
| "loss": 2.577, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 1.2025701082484015, | |
| "grad_norm": 1.3659100532531738, | |
| "learning_rate": 3.3295816919902464e-05, | |
| "loss": 2.6531, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 1.2152307400139266, | |
| "grad_norm": 1.156020998954773, | |
| "learning_rate": 3.3061339335959486e-05, | |
| "loss": 2.6418, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 1.2152307400139266, | |
| "eval_loss": 2.462512969970703, | |
| "eval_runtime": 40.8077, | |
| "eval_samples_per_second": 43.031, | |
| "eval_steps_per_second": 43.031, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 1.2278913717794517, | |
| "grad_norm": 1.7687715291976929, | |
| "learning_rate": 3.282686175201651e-05, | |
| "loss": 2.6085, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 1.2405520035449769, | |
| "grad_norm": 3.3047523498535156, | |
| "learning_rate": 3.2592384168073535e-05, | |
| "loss": 2.6002, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 1.253212635310502, | |
| "grad_norm": 1.040693998336792, | |
| "learning_rate": 3.2357906584130557e-05, | |
| "loss": 2.6145, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 1.265873267076027, | |
| "grad_norm": 0.9686591029167175, | |
| "learning_rate": 3.2123429000187585e-05, | |
| "loss": 2.5709, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.265873267076027, | |
| "eval_loss": 2.460991621017456, | |
| "eval_runtime": 40.9408, | |
| "eval_samples_per_second": 42.891, | |
| "eval_steps_per_second": 42.891, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.2785338988415522, | |
| "grad_norm": 1.2371070384979248, | |
| "learning_rate": 3.188895141624461e-05, | |
| "loss": 2.5449, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 1.2911945306070773, | |
| "grad_norm": 1.422345757484436, | |
| "learning_rate": 3.1654473832301634e-05, | |
| "loss": 2.6032, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 1.3038551623726025, | |
| "grad_norm": 2.229543447494507, | |
| "learning_rate": 3.1419996248358656e-05, | |
| "loss": 2.6611, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 1.3165157941381276, | |
| "grad_norm": 2.4649646282196045, | |
| "learning_rate": 3.1185518664415684e-05, | |
| "loss": 2.5963, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 1.3165157941381276, | |
| "eval_loss": 2.455350637435913, | |
| "eval_runtime": 40.876, | |
| "eval_samples_per_second": 42.959, | |
| "eval_steps_per_second": 42.959, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 1.3291764259036527, | |
| "grad_norm": 1.2330511808395386, | |
| "learning_rate": 3.095104108047271e-05, | |
| "loss": 2.5561, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 1.3418370576691778, | |
| "grad_norm": 2.1780569553375244, | |
| "learning_rate": 3.071656349652973e-05, | |
| "loss": 2.5878, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 1.3544976894347027, | |
| "grad_norm": 1.5878489017486572, | |
| "learning_rate": 3.048208591258676e-05, | |
| "loss": 2.5788, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 1.3671583212002278, | |
| "grad_norm": 1.2362117767333984, | |
| "learning_rate": 3.0247608328643783e-05, | |
| "loss": 2.685, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 1.3671583212002278, | |
| "eval_loss": 2.4557485580444336, | |
| "eval_runtime": 40.7838, | |
| "eval_samples_per_second": 43.056, | |
| "eval_steps_per_second": 43.056, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 1.379818952965753, | |
| "grad_norm": 1.4540385007858276, | |
| "learning_rate": 3.0013130744700808e-05, | |
| "loss": 2.5653, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 1.392479584731278, | |
| "grad_norm": 1.560059905052185, | |
| "learning_rate": 2.9778653160757836e-05, | |
| "loss": 2.5448, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.4051402164968032, | |
| "grad_norm": 3.153442144393921, | |
| "learning_rate": 2.9544175576814857e-05, | |
| "loss": 2.5042, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 1.4178008482623283, | |
| "grad_norm": 1.250948429107666, | |
| "learning_rate": 2.9309697992871882e-05, | |
| "loss": 2.575, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 1.4178008482623283, | |
| "eval_loss": 2.4553444385528564, | |
| "eval_runtime": 40.9798, | |
| "eval_samples_per_second": 42.85, | |
| "eval_steps_per_second": 42.85, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 1.4304614800278534, | |
| "grad_norm": 1.6559193134307861, | |
| "learning_rate": 2.907522040892891e-05, | |
| "loss": 2.6065, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 1.4431221117933786, | |
| "grad_norm": 1.6024394035339355, | |
| "learning_rate": 2.8840742824985935e-05, | |
| "loss": 2.5194, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 1.4557827435589035, | |
| "grad_norm": 1.3071702718734741, | |
| "learning_rate": 2.8606265241042956e-05, | |
| "loss": 2.5348, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 1.4684433753244286, | |
| "grad_norm": 1.1332521438598633, | |
| "learning_rate": 2.8371787657099984e-05, | |
| "loss": 2.5913, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 1.4684433753244286, | |
| "eval_loss": 2.454563617706299, | |
| "eval_runtime": 40.8474, | |
| "eval_samples_per_second": 42.989, | |
| "eval_steps_per_second": 42.989, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 1.4811040070899537, | |
| "grad_norm": 1.260486364364624, | |
| "learning_rate": 2.813731007315701e-05, | |
| "loss": 2.612, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 1.4937646388554788, | |
| "grad_norm": 1.009621500968933, | |
| "learning_rate": 2.790283248921403e-05, | |
| "loss": 2.6078, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 1.506425270621004, | |
| "grad_norm": 1.3116769790649414, | |
| "learning_rate": 2.766835490527106e-05, | |
| "loss": 2.5739, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 1.519085902386529, | |
| "grad_norm": 2.485499143600464, | |
| "learning_rate": 2.7433877321328083e-05, | |
| "loss": 2.6272, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.519085902386529, | |
| "eval_loss": 2.450514316558838, | |
| "eval_runtime": 40.6819, | |
| "eval_samples_per_second": 43.164, | |
| "eval_steps_per_second": 43.164, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.5317465341520542, | |
| "grad_norm": 1.934110164642334, | |
| "learning_rate": 2.7199399737385105e-05, | |
| "loss": 2.5319, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 1.5444071659175793, | |
| "grad_norm": 1.9517920017242432, | |
| "learning_rate": 2.6964922153442136e-05, | |
| "loss": 2.5759, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 1.5570677976831044, | |
| "grad_norm": 1.3010960817337036, | |
| "learning_rate": 2.6730444569499157e-05, | |
| "loss": 2.5811, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 1.5697284294486296, | |
| "grad_norm": 2.7256052494049072, | |
| "learning_rate": 2.6495966985556182e-05, | |
| "loss": 2.6294, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 1.5697284294486296, | |
| "eval_loss": 2.4498414993286133, | |
| "eval_runtime": 41.0253, | |
| "eval_samples_per_second": 42.803, | |
| "eval_steps_per_second": 42.803, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 1.5823890612141547, | |
| "grad_norm": 1.6172245740890503, | |
| "learning_rate": 2.626148940161321e-05, | |
| "loss": 2.6309, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 1.5950496929796798, | |
| "grad_norm": 1.3149018287658691, | |
| "learning_rate": 2.6027011817670232e-05, | |
| "loss": 2.5658, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 1.607710324745205, | |
| "grad_norm": 1.6285394430160522, | |
| "learning_rate": 2.5792534233727257e-05, | |
| "loss": 2.611, | |
| "step": 6350 | |
| }, | |
| { | |
| "epoch": 1.62037095651073, | |
| "grad_norm": 2.0910215377807617, | |
| "learning_rate": 2.5558056649784285e-05, | |
| "loss": 2.6277, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 1.62037095651073, | |
| "eval_loss": 2.449920892715454, | |
| "eval_runtime": 40.7694, | |
| "eval_samples_per_second": 43.071, | |
| "eval_steps_per_second": 43.071, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 1.633031588276255, | |
| "grad_norm": 1.497223138809204, | |
| "learning_rate": 2.5323579065841306e-05, | |
| "loss": 2.6336, | |
| "step": 6450 | |
| }, | |
| { | |
| "epoch": 1.64569222004178, | |
| "grad_norm": 1.3010990619659424, | |
| "learning_rate": 2.508910148189833e-05, | |
| "loss": 2.5497, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.6583528518073052, | |
| "grad_norm": 1.4681612253189087, | |
| "learning_rate": 2.4854623897955356e-05, | |
| "loss": 2.5628, | |
| "step": 6550 | |
| }, | |
| { | |
| "epoch": 1.6710134835728303, | |
| "grad_norm": 1.3477168083190918, | |
| "learning_rate": 2.4620146314012384e-05, | |
| "loss": 2.5352, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 1.6710134835728303, | |
| "eval_loss": 2.4485294818878174, | |
| "eval_runtime": 40.856, | |
| "eval_samples_per_second": 42.98, | |
| "eval_steps_per_second": 42.98, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 1.6836741153383554, | |
| "grad_norm": 1.2609894275665283, | |
| "learning_rate": 2.4385668730069405e-05, | |
| "loss": 2.5984, | |
| "step": 6650 | |
| }, | |
| { | |
| "epoch": 1.6963347471038803, | |
| "grad_norm": 1.498071312904358, | |
| "learning_rate": 2.415119114612643e-05, | |
| "loss": 2.6117, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 1.7089953788694054, | |
| "grad_norm": 1.5235400199890137, | |
| "learning_rate": 2.3916713562183458e-05, | |
| "loss": 2.6127, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 1.7216560106349306, | |
| "grad_norm": 1.7103843688964844, | |
| "learning_rate": 2.368223597824048e-05, | |
| "loss": 2.5761, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 1.7216560106349306, | |
| "eval_loss": 2.4469785690307617, | |
| "eval_runtime": 40.7827, | |
| "eval_samples_per_second": 43.058, | |
| "eval_steps_per_second": 43.058, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 1.7343166424004557, | |
| "grad_norm": 1.2467267513275146, | |
| "learning_rate": 2.3447758394297507e-05, | |
| "loss": 2.6174, | |
| "step": 6850 | |
| }, | |
| { | |
| "epoch": 1.7469772741659808, | |
| "grad_norm": 1.8229267597198486, | |
| "learning_rate": 2.3213280810354532e-05, | |
| "loss": 2.6364, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 1.759637905931506, | |
| "grad_norm": 2.1323461532592773, | |
| "learning_rate": 2.2978803226411554e-05, | |
| "loss": 2.5595, | |
| "step": 6950 | |
| }, | |
| { | |
| "epoch": 1.772298537697031, | |
| "grad_norm": 1.150225043296814, | |
| "learning_rate": 2.2744325642468582e-05, | |
| "loss": 2.6266, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.772298537697031, | |
| "eval_loss": 2.445380926132202, | |
| "eval_runtime": 40.7346, | |
| "eval_samples_per_second": 43.108, | |
| "eval_steps_per_second": 43.108, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.7849591694625562, | |
| "grad_norm": 1.36672842502594, | |
| "learning_rate": 2.2509848058525606e-05, | |
| "loss": 2.6212, | |
| "step": 7050 | |
| }, | |
| { | |
| "epoch": 1.7976198012280813, | |
| "grad_norm": 1.244776725769043, | |
| "learning_rate": 2.227537047458263e-05, | |
| "loss": 2.5734, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 1.8102804329936064, | |
| "grad_norm": 1.3731275796890259, | |
| "learning_rate": 2.2040892890639656e-05, | |
| "loss": 2.536, | |
| "step": 7150 | |
| }, | |
| { | |
| "epoch": 1.8229410647591315, | |
| "grad_norm": 2.2051963806152344, | |
| "learning_rate": 2.180641530669668e-05, | |
| "loss": 2.6097, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 1.8229410647591315, | |
| "eval_loss": 2.4447412490844727, | |
| "eval_runtime": 40.7537, | |
| "eval_samples_per_second": 43.088, | |
| "eval_steps_per_second": 43.088, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 1.8356016965246567, | |
| "grad_norm": 1.2323483228683472, | |
| "learning_rate": 2.1571937722753706e-05, | |
| "loss": 2.555, | |
| "step": 7250 | |
| }, | |
| { | |
| "epoch": 1.8482623282901818, | |
| "grad_norm": 1.0700924396514893, | |
| "learning_rate": 2.133746013881073e-05, | |
| "loss": 2.5598, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 1.860922960055707, | |
| "grad_norm": 2.785604238510132, | |
| "learning_rate": 2.1102982554867755e-05, | |
| "loss": 2.5682, | |
| "step": 7350 | |
| }, | |
| { | |
| "epoch": 1.873583591821232, | |
| "grad_norm": 1.6302391290664673, | |
| "learning_rate": 2.086850497092478e-05, | |
| "loss": 2.6002, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 1.873583591821232, | |
| "eval_loss": 2.4443070888519287, | |
| "eval_runtime": 40.7834, | |
| "eval_samples_per_second": 43.057, | |
| "eval_steps_per_second": 43.057, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 1.8862442235867571, | |
| "grad_norm": 1.270948886871338, | |
| "learning_rate": 2.0634027386981805e-05, | |
| "loss": 2.5563, | |
| "step": 7450 | |
| }, | |
| { | |
| "epoch": 1.898904855352282, | |
| "grad_norm": 1.0166101455688477, | |
| "learning_rate": 2.0399549803038833e-05, | |
| "loss": 2.5687, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.9115654871178072, | |
| "grad_norm": 1.4803165197372437, | |
| "learning_rate": 2.0165072219095854e-05, | |
| "loss": 2.5689, | |
| "step": 7550 | |
| }, | |
| { | |
| "epoch": 1.9242261188833323, | |
| "grad_norm": 1.66029953956604, | |
| "learning_rate": 1.993059463515288e-05, | |
| "loss": 2.5815, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 1.9242261188833323, | |
| "eval_loss": 2.4443864822387695, | |
| "eval_runtime": 40.8884, | |
| "eval_samples_per_second": 42.946, | |
| "eval_steps_per_second": 42.946, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 1.9368867506488574, | |
| "grad_norm": 1.5316967964172363, | |
| "learning_rate": 1.9696117051209907e-05, | |
| "loss": 2.5979, | |
| "step": 7650 | |
| }, | |
| { | |
| "epoch": 1.9495473824143825, | |
| "grad_norm": 1.3586021661758423, | |
| "learning_rate": 1.946163946726693e-05, | |
| "loss": 2.6304, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 1.9622080141799074, | |
| "grad_norm": 2.293283462524414, | |
| "learning_rate": 1.9227161883323953e-05, | |
| "loss": 2.5601, | |
| "step": 7750 | |
| }, | |
| { | |
| "epoch": 1.9748686459454325, | |
| "grad_norm": 1.6579082012176514, | |
| "learning_rate": 1.899268429938098e-05, | |
| "loss": 2.5124, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 1.9748686459454325, | |
| "eval_loss": 2.443239688873291, | |
| "eval_runtime": 41.5253, | |
| "eval_samples_per_second": 42.288, | |
| "eval_steps_per_second": 42.288, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 1.9875292777109577, | |
| "grad_norm": 1.2292983531951904, | |
| "learning_rate": 1.8758206715438003e-05, | |
| "loss": 2.5449, | |
| "step": 7850 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 2.1584088802337646, | |
| "learning_rate": 1.852372913149503e-05, | |
| "loss": 2.576, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 2.012660631765525, | |
| "grad_norm": 1.248931646347046, | |
| "learning_rate": 1.8289251547552055e-05, | |
| "loss": 2.5218, | |
| "step": 7950 | |
| }, | |
| { | |
| "epoch": 2.0253212635310502, | |
| "grad_norm": 1.5526643991470337, | |
| "learning_rate": 1.8054773963609077e-05, | |
| "loss": 2.5839, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.0253212635310502, | |
| "eval_loss": 2.4422366619110107, | |
| "eval_runtime": 41.5286, | |
| "eval_samples_per_second": 42.284, | |
| "eval_steps_per_second": 42.284, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.0379818952965754, | |
| "grad_norm": 1.4182465076446533, | |
| "learning_rate": 1.7820296379666105e-05, | |
| "loss": 2.5597, | |
| "step": 8050 | |
| }, | |
| { | |
| "epoch": 2.0506425270621005, | |
| "grad_norm": 1.2547794580459595, | |
| "learning_rate": 1.758581879572313e-05, | |
| "loss": 2.7643, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 2.0633031588276256, | |
| "grad_norm": 1.093676209449768, | |
| "learning_rate": 1.7351341211780155e-05, | |
| "loss": 2.5877, | |
| "step": 8150 | |
| }, | |
| { | |
| "epoch": 2.0759637905931507, | |
| "grad_norm": 2.055103302001953, | |
| "learning_rate": 1.711686362783718e-05, | |
| "loss": 2.4874, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 2.0759637905931507, | |
| "eval_loss": 2.4419164657592773, | |
| "eval_runtime": 40.7627, | |
| "eval_samples_per_second": 43.079, | |
| "eval_steps_per_second": 43.079, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 2.088624422358676, | |
| "grad_norm": 1.0890482664108276, | |
| "learning_rate": 1.6882386043894204e-05, | |
| "loss": 2.5942, | |
| "step": 8250 | |
| }, | |
| { | |
| "epoch": 2.101285054124201, | |
| "grad_norm": 1.8730581998825073, | |
| "learning_rate": 1.6647908459951232e-05, | |
| "loss": 2.592, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 2.113945685889726, | |
| "grad_norm": 1.6372568607330322, | |
| "learning_rate": 1.6413430876008254e-05, | |
| "loss": 2.5051, | |
| "step": 8350 | |
| }, | |
| { | |
| "epoch": 2.126606317655251, | |
| "grad_norm": 1.4793121814727783, | |
| "learning_rate": 1.6178953292065278e-05, | |
| "loss": 2.5644, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 2.126606317655251, | |
| "eval_loss": 2.44052791595459, | |
| "eval_runtime": 40.8302, | |
| "eval_samples_per_second": 43.007, | |
| "eval_steps_per_second": 43.007, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 2.139266949420776, | |
| "grad_norm": 1.4595574140548706, | |
| "learning_rate": 1.5944475708122306e-05, | |
| "loss": 2.6267, | |
| "step": 8450 | |
| }, | |
| { | |
| "epoch": 2.151927581186301, | |
| "grad_norm": 1.3399115800857544, | |
| "learning_rate": 1.5709998124179328e-05, | |
| "loss": 2.5277, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 2.164588212951826, | |
| "grad_norm": 1.6734541654586792, | |
| "learning_rate": 1.5480210091915216e-05, | |
| "loss": 2.5633, | |
| "step": 8550 | |
| }, | |
| { | |
| "epoch": 2.1772488447173513, | |
| "grad_norm": 1.5579371452331543, | |
| "learning_rate": 1.5245732507972238e-05, | |
| "loss": 2.5467, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 2.1772488447173513, | |
| "eval_loss": 2.4398272037506104, | |
| "eval_runtime": 40.8947, | |
| "eval_samples_per_second": 42.94, | |
| "eval_steps_per_second": 42.94, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 2.1899094764828764, | |
| "grad_norm": 1.932307243347168, | |
| "learning_rate": 1.5011254924029264e-05, | |
| "loss": 2.6112, | |
| "step": 8650 | |
| }, | |
| { | |
| "epoch": 2.2025701082484015, | |
| "grad_norm": 1.9798572063446045, | |
| "learning_rate": 1.4776777340086289e-05, | |
| "loss": 2.5891, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 2.2152307400139266, | |
| "grad_norm": 1.8812506198883057, | |
| "learning_rate": 1.4542299756143312e-05, | |
| "loss": 2.5659, | |
| "step": 8750 | |
| }, | |
| { | |
| "epoch": 2.2278913717794517, | |
| "grad_norm": 1.5422954559326172, | |
| "learning_rate": 1.4307822172200339e-05, | |
| "loss": 2.5315, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 2.2278913717794517, | |
| "eval_loss": 2.439927816390991, | |
| "eval_runtime": 40.7058, | |
| "eval_samples_per_second": 43.139, | |
| "eval_steps_per_second": 43.139, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 2.240552003544977, | |
| "grad_norm": 1.2686810493469238, | |
| "learning_rate": 1.4073344588257365e-05, | |
| "loss": 2.5809, | |
| "step": 8850 | |
| }, | |
| { | |
| "epoch": 2.253212635310502, | |
| "grad_norm": 1.905816674232483, | |
| "learning_rate": 1.3838867004314388e-05, | |
| "loss": 2.5225, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 2.265873267076027, | |
| "grad_norm": 1.9044383764266968, | |
| "learning_rate": 1.3604389420371413e-05, | |
| "loss": 2.5301, | |
| "step": 8950 | |
| }, | |
| { | |
| "epoch": 2.278533898841552, | |
| "grad_norm": 1.2211689949035645, | |
| "learning_rate": 1.336991183642844e-05, | |
| "loss": 2.5885, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 2.278533898841552, | |
| "eval_loss": 2.4387078285217285, | |
| "eval_runtime": 40.6013, | |
| "eval_samples_per_second": 43.25, | |
| "eval_steps_per_second": 43.25, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 2.2911945306070773, | |
| "grad_norm": 1.7181427478790283, | |
| "learning_rate": 1.3135434252485462e-05, | |
| "loss": 2.5422, | |
| "step": 9050 | |
| }, | |
| { | |
| "epoch": 2.3038551623726025, | |
| "grad_norm": 1.714859127998352, | |
| "learning_rate": 1.2900956668542489e-05, | |
| "loss": 2.4957, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 2.3165157941381276, | |
| "grad_norm": 1.473822832107544, | |
| "learning_rate": 1.2666479084599514e-05, | |
| "loss": 2.606, | |
| "step": 9150 | |
| }, | |
| { | |
| "epoch": 2.3291764259036527, | |
| "grad_norm": 1.6518057584762573, | |
| "learning_rate": 1.2432001500656538e-05, | |
| "loss": 2.5488, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 2.3291764259036527, | |
| "eval_loss": 2.438912868499756, | |
| "eval_runtime": 40.9773, | |
| "eval_samples_per_second": 42.853, | |
| "eval_steps_per_second": 42.853, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 2.341837057669178, | |
| "grad_norm": 1.0921835899353027, | |
| "learning_rate": 1.2197523916713563e-05, | |
| "loss": 2.5456, | |
| "step": 9250 | |
| }, | |
| { | |
| "epoch": 2.354497689434703, | |
| "grad_norm": 2.0887908935546875, | |
| "learning_rate": 1.1963046332770588e-05, | |
| "loss": 2.5298, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 2.367158321200228, | |
| "grad_norm": 2.09403133392334, | |
| "learning_rate": 1.1728568748827613e-05, | |
| "loss": 2.5843, | |
| "step": 9350 | |
| }, | |
| { | |
| "epoch": 2.3798189529657527, | |
| "grad_norm": 1.2155842781066895, | |
| "learning_rate": 1.1494091164884637e-05, | |
| "loss": 2.639, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 2.3798189529657527, | |
| "eval_loss": 2.4376986026763916, | |
| "eval_runtime": 40.7687, | |
| "eval_samples_per_second": 43.072, | |
| "eval_steps_per_second": 43.072, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 2.3924795847312783, | |
| "grad_norm": 1.2745308876037598, | |
| "learning_rate": 1.1259613580941662e-05, | |
| "loss": 2.572, | |
| "step": 9450 | |
| }, | |
| { | |
| "epoch": 2.405140216496803, | |
| "grad_norm": 1.243294358253479, | |
| "learning_rate": 1.1025135996998689e-05, | |
| "loss": 2.6086, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 2.417800848262328, | |
| "grad_norm": 1.3740507364273071, | |
| "learning_rate": 1.0790658413055713e-05, | |
| "loss": 2.5203, | |
| "step": 9550 | |
| }, | |
| { | |
| "epoch": 2.4304614800278532, | |
| "grad_norm": 1.3419544696807861, | |
| "learning_rate": 1.0556180829112736e-05, | |
| "loss": 2.4968, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 2.4304614800278532, | |
| "eval_loss": 2.4370713233947754, | |
| "eval_runtime": 40.6311, | |
| "eval_samples_per_second": 43.218, | |
| "eval_steps_per_second": 43.218, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 2.4431221117933783, | |
| "grad_norm": 1.2722185850143433, | |
| "learning_rate": 1.0321703245169763e-05, | |
| "loss": 2.617, | |
| "step": 9650 | |
| }, | |
| { | |
| "epoch": 2.4557827435589035, | |
| "grad_norm": 1.336860179901123, | |
| "learning_rate": 1.0087225661226788e-05, | |
| "loss": 2.5443, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 2.4684433753244286, | |
| "grad_norm": 1.5844101905822754, | |
| "learning_rate": 9.852748077283812e-06, | |
| "loss": 2.5358, | |
| "step": 9750 | |
| }, | |
| { | |
| "epoch": 2.4811040070899537, | |
| "grad_norm": 1.376717209815979, | |
| "learning_rate": 9.618270493340837e-06, | |
| "loss": 2.5065, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 2.4811040070899537, | |
| "eval_loss": 2.4364349842071533, | |
| "eval_runtime": 40.68, | |
| "eval_samples_per_second": 43.166, | |
| "eval_steps_per_second": 43.166, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 2.493764638855479, | |
| "grad_norm": 2.2268385887145996, | |
| "learning_rate": 9.383792909397862e-06, | |
| "loss": 2.5043, | |
| "step": 9850 | |
| }, | |
| { | |
| "epoch": 2.506425270621004, | |
| "grad_norm": 1.304364800453186, | |
| "learning_rate": 9.149315325454887e-06, | |
| "loss": 2.5213, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 2.519085902386529, | |
| "grad_norm": 1.662419319152832, | |
| "learning_rate": 8.914837741511913e-06, | |
| "loss": 2.6088, | |
| "step": 9950 | |
| }, | |
| { | |
| "epoch": 2.531746534152054, | |
| "grad_norm": 3.155359983444214, | |
| "learning_rate": 8.680360157568938e-06, | |
| "loss": 2.5311, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 2.531746534152054, | |
| "eval_loss": 2.4357810020446777, | |
| "eval_runtime": 40.7194, | |
| "eval_samples_per_second": 43.124, | |
| "eval_steps_per_second": 43.124, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 2.5444071659175793, | |
| "grad_norm": 1.9857499599456787, | |
| "learning_rate": 8.44588257362596e-06, | |
| "loss": 2.5105, | |
| "step": 10050 | |
| }, | |
| { | |
| "epoch": 2.5570677976831044, | |
| "grad_norm": 1.383115530014038, | |
| "learning_rate": 8.211404989682987e-06, | |
| "loss": 2.5388, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 2.5697284294486296, | |
| "grad_norm": 2.1307530403137207, | |
| "learning_rate": 7.976927405740012e-06, | |
| "loss": 2.5422, | |
| "step": 10150 | |
| }, | |
| { | |
| "epoch": 2.5823890612141547, | |
| "grad_norm": 1.7428008317947388, | |
| "learning_rate": 7.742449821797037e-06, | |
| "loss": 2.5139, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 2.5823890612141547, | |
| "eval_loss": 2.4361467361450195, | |
| "eval_runtime": 40.6659, | |
| "eval_samples_per_second": 43.181, | |
| "eval_steps_per_second": 43.181, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 2.59504969297968, | |
| "grad_norm": 1.9510554075241089, | |
| "learning_rate": 7.507972237854062e-06, | |
| "loss": 2.6383, | |
| "step": 10250 | |
| }, | |
| { | |
| "epoch": 2.607710324745205, | |
| "grad_norm": 1.658544898033142, | |
| "learning_rate": 7.273494653911086e-06, | |
| "loss": 2.5507, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 2.62037095651073, | |
| "grad_norm": 1.4996962547302246, | |
| "learning_rate": 7.039017069968111e-06, | |
| "loss": 2.5093, | |
| "step": 10350 | |
| }, | |
| { | |
| "epoch": 2.633031588276255, | |
| "grad_norm": 1.6710158586502075, | |
| "learning_rate": 6.804539486025137e-06, | |
| "loss": 2.6495, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 2.633031588276255, | |
| "eval_loss": 2.435485601425171, | |
| "eval_runtime": 40.7734, | |
| "eval_samples_per_second": 43.067, | |
| "eval_steps_per_second": 43.067, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 2.64569222004178, | |
| "grad_norm": 1.3965766429901123, | |
| "learning_rate": 6.570061902082161e-06, | |
| "loss": 2.5756, | |
| "step": 10450 | |
| }, | |
| { | |
| "epoch": 2.6583528518073054, | |
| "grad_norm": 1.1116695404052734, | |
| "learning_rate": 6.335584318139186e-06, | |
| "loss": 2.584, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 2.67101348357283, | |
| "grad_norm": 1.0421807765960693, | |
| "learning_rate": 6.101106734196211e-06, | |
| "loss": 2.5244, | |
| "step": 10550 | |
| }, | |
| { | |
| "epoch": 2.6836741153383556, | |
| "grad_norm": 1.374508023262024, | |
| "learning_rate": 5.8666291502532365e-06, | |
| "loss": 2.5097, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 2.6836741153383556, | |
| "eval_loss": 2.4343748092651367, | |
| "eval_runtime": 40.8106, | |
| "eval_samples_per_second": 43.028, | |
| "eval_steps_per_second": 43.028, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 2.6963347471038803, | |
| "grad_norm": 1.139459252357483, | |
| "learning_rate": 5.632151566310261e-06, | |
| "loss": 2.586, | |
| "step": 10650 | |
| }, | |
| { | |
| "epoch": 2.7089953788694054, | |
| "grad_norm": 1.1283456087112427, | |
| "learning_rate": 5.397673982367286e-06, | |
| "loss": 2.5461, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 2.7216560106349306, | |
| "grad_norm": 1.2529475688934326, | |
| "learning_rate": 5.163196398424311e-06, | |
| "loss": 2.5577, | |
| "step": 10750 | |
| }, | |
| { | |
| "epoch": 2.7343166424004557, | |
| "grad_norm": 1.7139452695846558, | |
| "learning_rate": 4.928718814481336e-06, | |
| "loss": 2.5476, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 2.7343166424004557, | |
| "eval_loss": 2.435107707977295, | |
| "eval_runtime": 40.9961, | |
| "eval_samples_per_second": 42.833, | |
| "eval_steps_per_second": 42.833, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 2.746977274165981, | |
| "grad_norm": 1.3778159618377686, | |
| "learning_rate": 4.69424123053836e-06, | |
| "loss": 2.5561, | |
| "step": 10850 | |
| }, | |
| { | |
| "epoch": 2.759637905931506, | |
| "grad_norm": 1.0923840999603271, | |
| "learning_rate": 4.459763646595386e-06, | |
| "loss": 2.5184, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 2.772298537697031, | |
| "grad_norm": 1.2169151306152344, | |
| "learning_rate": 4.225286062652411e-06, | |
| "loss": 2.6378, | |
| "step": 10950 | |
| }, | |
| { | |
| "epoch": 2.784959169462556, | |
| "grad_norm": 1.5901875495910645, | |
| "learning_rate": 3.9908084787094354e-06, | |
| "loss": 2.6822, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 2.784959169462556, | |
| "eval_loss": 2.434779644012451, | |
| "eval_runtime": 40.6453, | |
| "eval_samples_per_second": 43.203, | |
| "eval_steps_per_second": 43.203, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 2.7976198012280813, | |
| "grad_norm": 1.7463274002075195, | |
| "learning_rate": 3.7563308947664606e-06, | |
| "loss": 2.5749, | |
| "step": 11050 | |
| }, | |
| { | |
| "epoch": 2.8102804329936064, | |
| "grad_norm": 1.236441731452942, | |
| "learning_rate": 3.521853310823486e-06, | |
| "loss": 2.5416, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 2.8229410647591315, | |
| "grad_norm": 1.132720708847046, | |
| "learning_rate": 3.28737572688051e-06, | |
| "loss": 2.597, | |
| "step": 11150 | |
| }, | |
| { | |
| "epoch": 2.8356016965246567, | |
| "grad_norm": 2.339376926422119, | |
| "learning_rate": 3.0528981429375353e-06, | |
| "loss": 2.5564, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 2.8356016965246567, | |
| "eval_loss": 2.4349372386932373, | |
| "eval_runtime": 40.7164, | |
| "eval_samples_per_second": 43.128, | |
| "eval_steps_per_second": 43.128, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 2.8482623282901818, | |
| "grad_norm": 1.878458857536316, | |
| "learning_rate": 2.81842055899456e-06, | |
| "loss": 2.6238, | |
| "step": 11250 | |
| }, | |
| { | |
| "epoch": 2.860922960055707, | |
| "grad_norm": 1.8116399049758911, | |
| "learning_rate": 2.5839429750515852e-06, | |
| "loss": 2.5114, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 2.873583591821232, | |
| "grad_norm": 1.155181884765625, | |
| "learning_rate": 2.34946539110861e-06, | |
| "loss": 2.5582, | |
| "step": 11350 | |
| }, | |
| { | |
| "epoch": 2.886244223586757, | |
| "grad_norm": 1.505588173866272, | |
| "learning_rate": 2.1149878071656348e-06, | |
| "loss": 2.6288, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 2.886244223586757, | |
| "eval_loss": 2.434521436691284, | |
| "eval_runtime": 41.0956, | |
| "eval_samples_per_second": 42.73, | |
| "eval_steps_per_second": 42.73, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 2.8989048553522823, | |
| "grad_norm": 1.4831116199493408, | |
| "learning_rate": 1.8805102232226601e-06, | |
| "loss": 2.4811, | |
| "step": 11450 | |
| }, | |
| { | |
| "epoch": 2.911565487117807, | |
| "grad_norm": 1.931284785270691, | |
| "learning_rate": 1.646032639279685e-06, | |
| "loss": 2.5426, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 2.9242261188833325, | |
| "grad_norm": 1.6025974750518799, | |
| "learning_rate": 1.4115550553367099e-06, | |
| "loss": 2.509, | |
| "step": 11550 | |
| }, | |
| { | |
| "epoch": 2.936886750648857, | |
| "grad_norm": 1.3426520824432373, | |
| "learning_rate": 1.1770774713937348e-06, | |
| "loss": 2.6057, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 2.936886750648857, | |
| "eval_loss": 2.4339404106140137, | |
| "eval_runtime": 41.3931, | |
| "eval_samples_per_second": 42.423, | |
| "eval_steps_per_second": 42.423, | |
| "step": 11600 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 11847, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6118984656617472.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |