| { | |
| "best_metric": 0.21060962975025177, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-150", | |
| "epoch": 1.3245033112582782, | |
| "eval_steps": 25, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008830022075055188, | |
| "grad_norm": 0.539530336856842, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 0.7436, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008830022075055188, | |
| "eval_loss": 0.7710736989974976, | |
| "eval_runtime": 8.9925, | |
| "eval_samples_per_second": 5.56, | |
| "eval_steps_per_second": 0.778, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.017660044150110375, | |
| "grad_norm": 0.6179248094558716, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 0.8066, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.026490066225165563, | |
| "grad_norm": 0.6645671725273132, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 0.8396, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03532008830022075, | |
| "grad_norm": 0.6200567483901978, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 0.7884, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04415011037527594, | |
| "grad_norm": 0.5380943417549133, | |
| "learning_rate": 0.00015, | |
| "loss": 0.5853, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.052980132450331126, | |
| "grad_norm": 0.5036277174949646, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 0.5389, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06181015452538632, | |
| "grad_norm": 0.6514653563499451, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 0.4683, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0706401766004415, | |
| "grad_norm": 0.9316419959068298, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 0.54, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07947019867549669, | |
| "grad_norm": 0.5196866989135742, | |
| "learning_rate": 0.00027, | |
| "loss": 0.4545, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08830022075055188, | |
| "grad_norm": 0.5413261651992798, | |
| "learning_rate": 0.0003, | |
| "loss": 0.4244, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09713024282560706, | |
| "grad_norm": 0.5664142966270447, | |
| "learning_rate": 0.0002999794957488703, | |
| "loss": 0.3903, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.10596026490066225, | |
| "grad_norm": 0.6020936965942383, | |
| "learning_rate": 0.0002999179886011389, | |
| "loss": 0.4023, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.11479028697571744, | |
| "grad_norm": 0.49377548694610596, | |
| "learning_rate": 0.0002998154953722457, | |
| "loss": 0.3985, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.12362030905077263, | |
| "grad_norm": 0.39252859354019165, | |
| "learning_rate": 0.00029967204408281613, | |
| "loss": 0.3617, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.13245033112582782, | |
| "grad_norm": 0.4053530991077423, | |
| "learning_rate": 0.00029948767395100045, | |
| "loss": 0.3259, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.141280353200883, | |
| "grad_norm": 0.4019186794757843, | |
| "learning_rate": 0.0002992624353817517, | |
| "loss": 0.3568, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.15011037527593818, | |
| "grad_norm": 0.38053813576698303, | |
| "learning_rate": 0.0002989963899530457, | |
| "loss": 0.3454, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.15894039735099338, | |
| "grad_norm": 0.3768708407878876, | |
| "learning_rate": 0.00029868961039904624, | |
| "loss": 0.3432, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.16777041942604856, | |
| "grad_norm": 0.33955276012420654, | |
| "learning_rate": 0.00029834218059022024, | |
| "loss": 0.3089, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.17660044150110377, | |
| "grad_norm": 0.31420886516571045, | |
| "learning_rate": 0.00029795419551040833, | |
| "loss": 0.2576, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.18543046357615894, | |
| "grad_norm": 0.3766714036464691, | |
| "learning_rate": 0.00029752576123085736, | |
| "loss": 0.3017, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.19426048565121412, | |
| "grad_norm": 0.4495747983455658, | |
| "learning_rate": 0.0002970569948812214, | |
| "loss": 0.2717, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.20309050772626933, | |
| "grad_norm": 0.3679252564907074, | |
| "learning_rate": 0.0002965480246175399, | |
| "loss": 0.2564, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2119205298013245, | |
| "grad_norm": 0.35804858803749084, | |
| "learning_rate": 0.0002959989895872009, | |
| "loss": 0.2278, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.22075055187637968, | |
| "grad_norm": 0.49645286798477173, | |
| "learning_rate": 0.0002954100398908995, | |
| "loss": 0.2242, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.22075055187637968, | |
| "eval_loss": 0.3220010995864868, | |
| "eval_runtime": 8.6165, | |
| "eval_samples_per_second": 5.803, | |
| "eval_steps_per_second": 0.812, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.22958057395143489, | |
| "grad_norm": 0.3857850730419159, | |
| "learning_rate": 0.0002947813365416023, | |
| "loss": 0.2466, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.23841059602649006, | |
| "grad_norm": 0.5409634113311768, | |
| "learning_rate": 0.0002941130514205272, | |
| "loss": 0.4729, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.24724061810154527, | |
| "grad_norm": 4.009927749633789, | |
| "learning_rate": 0.0002934053672301536, | |
| "loss": 1.4493, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.2560706401766004, | |
| "grad_norm": 0.3887677788734436, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 0.4336, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.26490066225165565, | |
| "grad_norm": 0.3323811888694763, | |
| "learning_rate": 0.00029187258625509513, | |
| "loss": 0.4117, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2737306843267108, | |
| "grad_norm": 0.2985091209411621, | |
| "learning_rate": 0.00029104790851742417, | |
| "loss": 0.3453, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.282560706401766, | |
| "grad_norm": 0.3181455731391907, | |
| "learning_rate": 0.0002901846696899191, | |
| "loss": 0.3032, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2913907284768212, | |
| "grad_norm": 0.27217257022857666, | |
| "learning_rate": 0.00028928310577345606, | |
| "loss": 0.2274, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.30022075055187636, | |
| "grad_norm": 0.2923267185688019, | |
| "learning_rate": 0.0002883434632466077, | |
| "loss": 0.2747, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.3090507726269316, | |
| "grad_norm": 0.31327348947525024, | |
| "learning_rate": 0.00028736599899825856, | |
| "loss": 0.2876, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.31788079470198677, | |
| "grad_norm": 0.2787221670150757, | |
| "learning_rate": 0.00028635098025737434, | |
| "loss": 0.2623, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.32671081677704195, | |
| "grad_norm": 0.2709098756313324, | |
| "learning_rate": 0.00028529868451994384, | |
| "loss": 0.2678, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.3355408388520971, | |
| "grad_norm": 0.32480549812316895, | |
| "learning_rate": 0.0002842093994731145, | |
| "loss": 0.2934, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.3443708609271523, | |
| "grad_norm": 0.2852940559387207, | |
| "learning_rate": 0.00028308342291654174, | |
| "loss": 0.2727, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.35320088300220753, | |
| "grad_norm": 0.27713730931282043, | |
| "learning_rate": 0.00028192106268097334, | |
| "loss": 0.2662, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3620309050772627, | |
| "grad_norm": 0.2732914090156555, | |
| "learning_rate": 0.00028072263654409154, | |
| "loss": 0.24, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3708609271523179, | |
| "grad_norm": 0.2701897919178009, | |
| "learning_rate": 0.0002794884721436361, | |
| "loss": 0.2617, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.37969094922737306, | |
| "grad_norm": 0.2648429572582245, | |
| "learning_rate": 0.00027821890688783083, | |
| "loss": 0.2488, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.38852097130242824, | |
| "grad_norm": 0.29421964287757874, | |
| "learning_rate": 0.0002769142878631403, | |
| "loss": 0.278, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.3973509933774834, | |
| "grad_norm": 0.25156694650650024, | |
| "learning_rate": 0.00027557497173937923, | |
| "loss": 0.248, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.40618101545253865, | |
| "grad_norm": 0.24106387794017792, | |
| "learning_rate": 0.000274201324672203, | |
| "loss": 0.2162, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.41501103752759383, | |
| "grad_norm": 0.27839741110801697, | |
| "learning_rate": 0.00027279372220300385, | |
| "loss": 0.2568, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.423841059602649, | |
| "grad_norm": 0.233811616897583, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 0.1938, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.4326710816777042, | |
| "grad_norm": 0.23097911477088928, | |
| "learning_rate": 0.00026987819953423867, | |
| "loss": 0.1853, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.44150110375275936, | |
| "grad_norm": 0.2746119499206543, | |
| "learning_rate": 0.00026837107640945905, | |
| "loss": 0.233, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.44150110375275936, | |
| "eval_loss": 0.26192525029182434, | |
| "eval_runtime": 8.6079, | |
| "eval_samples_per_second": 5.809, | |
| "eval_steps_per_second": 0.813, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4503311258278146, | |
| "grad_norm": 0.26269274950027466, | |
| "learning_rate": 0.0002668315918143169, | |
| "loss": 0.1918, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.45916114790286977, | |
| "grad_norm": 0.4410167336463928, | |
| "learning_rate": 0.00026526016662852886, | |
| "loss": 0.2198, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.46799116997792495, | |
| "grad_norm": 0.3116855025291443, | |
| "learning_rate": 0.00026365723046405023, | |
| "loss": 0.2459, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.4768211920529801, | |
| "grad_norm": 0.37757059931755066, | |
| "learning_rate": 0.0002620232215476231, | |
| "loss": 0.2896, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.4856512141280353, | |
| "grad_norm": 0.4453379511833191, | |
| "learning_rate": 0.0002603585866009697, | |
| "loss": 0.3244, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.49448123620309054, | |
| "grad_norm": 1.5678483247756958, | |
| "learning_rate": 0.00025866378071866334, | |
| "loss": 0.6317, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.5033112582781457, | |
| "grad_norm": 0.3457544147968292, | |
| "learning_rate": 0.00025693926724370956, | |
| "loss": 0.3821, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.5121412803532008, | |
| "grad_norm": 0.3128604292869568, | |
| "learning_rate": 0.00025518551764087326, | |
| "loss": 0.3191, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.5209713024282561, | |
| "grad_norm": 0.28137052059173584, | |
| "learning_rate": 0.00025340301136778483, | |
| "loss": 0.3323, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.5298013245033113, | |
| "grad_norm": 0.2762452960014343, | |
| "learning_rate": 0.00025159223574386114, | |
| "loss": 0.3163, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5386313465783664, | |
| "grad_norm": 0.26939550042152405, | |
| "learning_rate": 0.0002497536858170772, | |
| "loss": 0.2338, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.5474613686534217, | |
| "grad_norm": 0.25849199295043945, | |
| "learning_rate": 0.00024788786422862526, | |
| "loss": 0.24, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.5562913907284768, | |
| "grad_norm": 0.2425060272216797, | |
| "learning_rate": 0.00024599528107549745, | |
| "loss": 0.234, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.565121412803532, | |
| "grad_norm": 0.23768416047096252, | |
| "learning_rate": 0.00024407645377103054, | |
| "loss": 0.2171, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.5739514348785872, | |
| "grad_norm": 0.2728182077407837, | |
| "learning_rate": 0.00024213190690345018, | |
| "loss": 0.227, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.5827814569536424, | |
| "grad_norm": 0.23953858017921448, | |
| "learning_rate": 0.00024016217209245374, | |
| "loss": 0.2238, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.5916114790286976, | |
| "grad_norm": 0.25809717178344727, | |
| "learning_rate": 0.00023816778784387094, | |
| "loss": 0.2426, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.6004415011037527, | |
| "grad_norm": 0.28087127208709717, | |
| "learning_rate": 0.0002361492994024415, | |
| "loss": 0.2699, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.609271523178808, | |
| "grad_norm": 0.25422003865242004, | |
| "learning_rate": 0.0002341072586027509, | |
| "loss": 0.2469, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.6181015452538632, | |
| "grad_norm": 0.271660178899765, | |
| "learning_rate": 0.00023204222371836405, | |
| "loss": 0.2638, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6269315673289183, | |
| "grad_norm": 0.25974762439727783, | |
| "learning_rate": 0.00022995475930919905, | |
| "loss": 0.2447, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.6357615894039735, | |
| "grad_norm": 0.23339006304740906, | |
| "learning_rate": 0.00022784543606718227, | |
| "loss": 0.2318, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.6445916114790287, | |
| "grad_norm": 0.2516346871852875, | |
| "learning_rate": 0.00022571483066022657, | |
| "loss": 0.2679, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.6534216335540839, | |
| "grad_norm": 0.2606465518474579, | |
| "learning_rate": 0.0002235635255745762, | |
| "loss": 0.2452, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.6622516556291391, | |
| "grad_norm": 0.2597995698451996, | |
| "learning_rate": 0.00022139210895556104, | |
| "loss": 0.1828, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.6622516556291391, | |
| "eval_loss": 0.23728808760643005, | |
| "eval_runtime": 9.0028, | |
| "eval_samples_per_second": 5.554, | |
| "eval_steps_per_second": 0.778, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.6710816777041942, | |
| "grad_norm": 0.2870580852031708, | |
| "learning_rate": 0.00021920117444680317, | |
| "loss": 0.222, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.6799116997792495, | |
| "grad_norm": 0.24285611510276794, | |
| "learning_rate": 0.00021699132102792097, | |
| "loss": 0.1982, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.6887417218543046, | |
| "grad_norm": 0.24280601739883423, | |
| "learning_rate": 0.0002147631528507739, | |
| "loss": 0.2086, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.6975717439293598, | |
| "grad_norm": 0.275769978761673, | |
| "learning_rate": 0.00021251727907429355, | |
| "loss": 0.2052, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.7064017660044151, | |
| "grad_norm": 0.2648524045944214, | |
| "learning_rate": 0.0002102543136979454, | |
| "loss": 0.204, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.7152317880794702, | |
| "grad_norm": 0.34556815028190613, | |
| "learning_rate": 0.0002079748753938678, | |
| "loss": 0.2676, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.7240618101545254, | |
| "grad_norm": 0.3545214831829071, | |
| "learning_rate": 0.0002056795873377331, | |
| "loss": 0.2618, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.7328918322295805, | |
| "grad_norm": 0.3948529064655304, | |
| "learning_rate": 0.00020336907703837748, | |
| "loss": 0.2681, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.7417218543046358, | |
| "grad_norm": 1.6499781608581543, | |
| "learning_rate": 0.00020104397616624645, | |
| "loss": 0.6606, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.7505518763796909, | |
| "grad_norm": 0.2808334529399872, | |
| "learning_rate": 0.00019870492038070252, | |
| "loss": 0.344, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.7593818984547461, | |
| "grad_norm": 0.27674341201782227, | |
| "learning_rate": 0.0001963525491562421, | |
| "loss": 0.3014, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.7682119205298014, | |
| "grad_norm": 0.2440793216228485, | |
| "learning_rate": 0.0001939875056076697, | |
| "loss": 0.3069, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.7770419426048565, | |
| "grad_norm": 0.2647138237953186, | |
| "learning_rate": 0.00019161043631427666, | |
| "loss": 0.28, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.7858719646799117, | |
| "grad_norm": 0.2215111255645752, | |
| "learning_rate": 0.00018922199114307294, | |
| "loss": 0.2274, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.7947019867549668, | |
| "grad_norm": 0.20203767716884613, | |
| "learning_rate": 0.00018682282307111987, | |
| "loss": 0.1834, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8035320088300221, | |
| "grad_norm": 0.23644301295280457, | |
| "learning_rate": 0.00018441358800701273, | |
| "loss": 0.244, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.8123620309050773, | |
| "grad_norm": 0.23923274874687195, | |
| "learning_rate": 0.00018199494461156203, | |
| "loss": 0.1987, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.8211920529801324, | |
| "grad_norm": 0.2625834047794342, | |
| "learning_rate": 0.000179567554117722, | |
| "loss": 0.2483, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.8300220750551877, | |
| "grad_norm": 0.2455959916114807, | |
| "learning_rate": 0.00017713208014981648, | |
| "loss": 0.2222, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.8388520971302428, | |
| "grad_norm": 0.2274852693080902, | |
| "learning_rate": 0.00017468918854211007, | |
| "loss": 0.2276, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.847682119205298, | |
| "grad_norm": 0.23596301674842834, | |
| "learning_rate": 0.00017223954715677627, | |
| "loss": 0.2226, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.8565121412803532, | |
| "grad_norm": 0.25137948989868164, | |
| "learning_rate": 0.00016978382570131034, | |
| "loss": 0.2432, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.8653421633554084, | |
| "grad_norm": 0.25432929396629333, | |
| "learning_rate": 0.00016732269554543794, | |
| "loss": 0.2066, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.8741721854304636, | |
| "grad_norm": 0.2482401430606842, | |
| "learning_rate": 0.00016485682953756942, | |
| "loss": 0.2212, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.8830022075055187, | |
| "grad_norm": 0.2436574399471283, | |
| "learning_rate": 0.00016238690182084986, | |
| "loss": 0.2298, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.8830022075055187, | |
| "eval_loss": 0.22081802785396576, | |
| "eval_runtime": 8.4385, | |
| "eval_samples_per_second": 5.925, | |
| "eval_steps_per_second": 0.83, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.891832229580574, | |
| "grad_norm": 0.2530083656311035, | |
| "learning_rate": 0.0001599135876488549, | |
| "loss": 0.2319, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.9006622516556292, | |
| "grad_norm": 0.21293362975120544, | |
| "learning_rate": 0.00015743756320098332, | |
| "loss": 0.1978, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.9094922737306843, | |
| "grad_norm": 0.25216004252433777, | |
| "learning_rate": 0.0001549595053975962, | |
| "loss": 0.1811, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.9183222958057395, | |
| "grad_norm": 0.23433512449264526, | |
| "learning_rate": 0.00015248009171495378, | |
| "loss": 0.2014, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.9271523178807947, | |
| "grad_norm": 0.20752263069152832, | |
| "learning_rate": 0.00015, | |
| "loss": 0.1645, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.9359823399558499, | |
| "grad_norm": 0.2603313624858856, | |
| "learning_rate": 0.00014751990828504622, | |
| "loss": 0.191, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.9448123620309051, | |
| "grad_norm": 0.27333831787109375, | |
| "learning_rate": 0.00014504049460240375, | |
| "loss": 0.2247, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.9536423841059603, | |
| "grad_norm": 0.24938559532165527, | |
| "learning_rate": 0.00014256243679901663, | |
| "loss": 0.1789, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.9624724061810155, | |
| "grad_norm": 0.2354554533958435, | |
| "learning_rate": 0.00014008641235114508, | |
| "loss": 0.1606, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.9713024282560706, | |
| "grad_norm": 0.3264496922492981, | |
| "learning_rate": 0.00013761309817915014, | |
| "loss": 0.2777, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.9801324503311258, | |
| "grad_norm": 0.3939518332481384, | |
| "learning_rate": 0.00013514317046243058, | |
| "loss": 0.3138, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.9889624724061811, | |
| "grad_norm": 1.1526501178741455, | |
| "learning_rate": 0.00013267730445456208, | |
| "loss": 0.5539, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.9977924944812362, | |
| "grad_norm": 0.2903338074684143, | |
| "learning_rate": 0.00013021617429868963, | |
| "loss": 0.2596, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 1.0066225165562914, | |
| "grad_norm": 0.6565661430358887, | |
| "learning_rate": 0.00012776045284322368, | |
| "loss": 0.5067, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.0154525386313467, | |
| "grad_norm": 0.2586728036403656, | |
| "learning_rate": 0.00012531081145788987, | |
| "loss": 0.2531, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.0242825607064017, | |
| "grad_norm": 0.2610194683074951, | |
| "learning_rate": 0.00012286791985018355, | |
| "loss": 0.2808, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.033112582781457, | |
| "grad_norm": 0.2583560049533844, | |
| "learning_rate": 0.00012043244588227796, | |
| "loss": 0.2729, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.0419426048565121, | |
| "grad_norm": 0.217752605676651, | |
| "learning_rate": 0.00011800505538843798, | |
| "loss": 0.2058, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.0507726269315674, | |
| "grad_norm": 0.2030157893896103, | |
| "learning_rate": 0.00011558641199298727, | |
| "loss": 0.1815, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 1.0596026490066226, | |
| "grad_norm": 0.20954853296279907, | |
| "learning_rate": 0.00011317717692888012, | |
| "loss": 0.1792, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.0684326710816776, | |
| "grad_norm": 0.18091771006584167, | |
| "learning_rate": 0.00011077800885692702, | |
| "loss": 0.1662, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 1.0772626931567328, | |
| "grad_norm": 0.20627768337726593, | |
| "learning_rate": 0.00010838956368572334, | |
| "loss": 0.1777, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 1.086092715231788, | |
| "grad_norm": 0.21561631560325623, | |
| "learning_rate": 0.0001060124943923303, | |
| "loss": 0.197, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 1.0949227373068433, | |
| "grad_norm": 0.24049685895442963, | |
| "learning_rate": 0.0001036474508437579, | |
| "loss": 0.1965, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 1.1037527593818985, | |
| "grad_norm": 0.2354094386100769, | |
| "learning_rate": 0.00010129507961929748, | |
| "loss": 0.1869, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.1037527593818985, | |
| "eval_loss": 0.21981161832809448, | |
| "eval_runtime": 7.9161, | |
| "eval_samples_per_second": 6.316, | |
| "eval_steps_per_second": 0.884, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.1125827814569536, | |
| "grad_norm": 0.24173709750175476, | |
| "learning_rate": 9.895602383375353e-05, | |
| "loss": 0.2063, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 1.1214128035320088, | |
| "grad_norm": 0.24440215528011322, | |
| "learning_rate": 9.663092296162251e-05, | |
| "loss": 0.1866, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 1.130242825607064, | |
| "grad_norm": 0.23964616656303406, | |
| "learning_rate": 9.432041266226686e-05, | |
| "loss": 0.1952, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 1.1390728476821192, | |
| "grad_norm": 0.23612673580646515, | |
| "learning_rate": 9.202512460613219e-05, | |
| "loss": 0.1978, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 1.1479028697571745, | |
| "grad_norm": 0.21302524209022522, | |
| "learning_rate": 8.97456863020546e-05, | |
| "loss": 0.1789, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.1567328918322295, | |
| "grad_norm": 0.22610829770565033, | |
| "learning_rate": 8.748272092570646e-05, | |
| "loss": 0.1921, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 1.1655629139072847, | |
| "grad_norm": 0.2158009558916092, | |
| "learning_rate": 8.523684714922608e-05, | |
| "loss": 0.1716, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 1.17439293598234, | |
| "grad_norm": 0.2384001463651657, | |
| "learning_rate": 8.300867897207903e-05, | |
| "loss": 0.1488, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 1.1832229580573952, | |
| "grad_norm": 0.20479005575180054, | |
| "learning_rate": 8.079882555319684e-05, | |
| "loss": 0.1429, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 1.1920529801324504, | |
| "grad_norm": 0.21124428510665894, | |
| "learning_rate": 7.860789104443896e-05, | |
| "loss": 0.1542, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.2008830022075054, | |
| "grad_norm": 0.2595142126083374, | |
| "learning_rate": 7.643647442542382e-05, | |
| "loss": 0.1562, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 1.2097130242825607, | |
| "grad_norm": 0.24693676829338074, | |
| "learning_rate": 7.428516933977347e-05, | |
| "loss": 0.1826, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 1.218543046357616, | |
| "grad_norm": 0.2386799454689026, | |
| "learning_rate": 7.215456393281776e-05, | |
| "loss": 0.1453, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 1.2273730684326711, | |
| "grad_norm": 0.292263388633728, | |
| "learning_rate": 7.004524069080096e-05, | |
| "loss": 0.2029, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 1.2362030905077264, | |
| "grad_norm": 0.30869174003601074, | |
| "learning_rate": 6.795777628163599e-05, | |
| "loss": 0.2001, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.2450331125827814, | |
| "grad_norm": 0.7546313405036926, | |
| "learning_rate": 6.58927413972491e-05, | |
| "loss": 0.33, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 1.2538631346578366, | |
| "grad_norm": 0.28588002920150757, | |
| "learning_rate": 6.385070059755846e-05, | |
| "loss": 0.1978, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 1.2626931567328918, | |
| "grad_norm": 0.3258229196071625, | |
| "learning_rate": 6.183221215612904e-05, | |
| "loss": 0.2734, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 1.271523178807947, | |
| "grad_norm": 0.2730714678764343, | |
| "learning_rate": 5.983782790754623e-05, | |
| "loss": 0.2314, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 1.280353200883002, | |
| "grad_norm": 0.2608177959918976, | |
| "learning_rate": 5.786809309654982e-05, | |
| "loss": 0.208, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.2891832229580573, | |
| "grad_norm": 0.20529748499393463, | |
| "learning_rate": 5.592354622896944e-05, | |
| "loss": 0.156, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 1.2980132450331126, | |
| "grad_norm": 0.19379666447639465, | |
| "learning_rate": 5.40047189245025e-05, | |
| "loss": 0.1629, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 1.3068432671081678, | |
| "grad_norm": 0.21285969018936157, | |
| "learning_rate": 5.211213577137469e-05, | |
| "loss": 0.1852, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 1.315673289183223, | |
| "grad_norm": 0.21158519387245178, | |
| "learning_rate": 5.024631418292274e-05, | |
| "loss": 0.171, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 1.3245033112582782, | |
| "grad_norm": 0.25292232632637024, | |
| "learning_rate": 4.840776425613886e-05, | |
| "loss": 0.2063, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.3245033112582782, | |
| "eval_loss": 0.21060962975025177, | |
| "eval_runtime": 8.6102, | |
| "eval_samples_per_second": 5.807, | |
| "eval_steps_per_second": 0.813, | |
| "step": 150 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.3180618957520896e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |