| { | |
| "best_metric": 0.14205443859100342, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-100", | |
| "epoch": 0.44958553833185033, | |
| "eval_steps": 25, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0029972369222123355, | |
| "grad_norm": 7.602510929107666, | |
| "learning_rate": 1.4999999999999999e-05, | |
| "loss": 7.3791, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0029972369222123355, | |
| "eval_loss": 5.100011348724365, | |
| "eval_runtime": 0.2905, | |
| "eval_samples_per_second": 172.095, | |
| "eval_steps_per_second": 44.745, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005994473844424671, | |
| "grad_norm": 5.811465263366699, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 5.2052, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.008991710766637007, | |
| "grad_norm": 6.1456217765808105, | |
| "learning_rate": 4.4999999999999996e-05, | |
| "loss": 5.0327, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.011988947688849342, | |
| "grad_norm": 5.857211112976074, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 4.9457, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.014986184611061678, | |
| "grad_norm": 5.512299537658691, | |
| "learning_rate": 7.5e-05, | |
| "loss": 4.8063, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.017983421533274015, | |
| "grad_norm": 5.282471179962158, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 4.7355, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02098065845548635, | |
| "grad_norm": 4.267989158630371, | |
| "learning_rate": 0.00010499999999999999, | |
| "loss": 4.4458, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.023977895377698684, | |
| "grad_norm": 3.799853801727295, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 4.2302, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02697513229991102, | |
| "grad_norm": 3.506157875061035, | |
| "learning_rate": 0.000135, | |
| "loss": 3.857, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.029972369222123357, | |
| "grad_norm": 3.8407812118530273, | |
| "learning_rate": 0.00015, | |
| "loss": 3.749, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03296960614433569, | |
| "grad_norm": 4.470568656921387, | |
| "learning_rate": 0.000165, | |
| "loss": 3.4078, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03596684306654803, | |
| "grad_norm": 4.822042465209961, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 3.0358, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.038964079988760364, | |
| "grad_norm": 5.060558795928955, | |
| "learning_rate": 0.000195, | |
| "loss": 4.5688, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0419613169109727, | |
| "grad_norm": 4.888822078704834, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 3.6099, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04495855383318503, | |
| "grad_norm": 3.4810433387756348, | |
| "learning_rate": 0.000225, | |
| "loss": 2.4291, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04795579075539737, | |
| "grad_norm": 3.577241897583008, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 2.1686, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0509530276776097, | |
| "grad_norm": 3.595766544342041, | |
| "learning_rate": 0.00025499999999999996, | |
| "loss": 1.9973, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.05395026459982204, | |
| "grad_norm": 4.025913715362549, | |
| "learning_rate": 0.00027, | |
| "loss": 1.9723, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05694750152203437, | |
| "grad_norm": 2.864335536956787, | |
| "learning_rate": 0.000285, | |
| "loss": 1.9312, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05994473844424671, | |
| "grad_norm": 3.9801218509674072, | |
| "learning_rate": 0.0003, | |
| "loss": 1.8875, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06294197536645904, | |
| "grad_norm": 3.2217376232147217, | |
| "learning_rate": 0.00029999841345404617, | |
| "loss": 1.5763, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06593921228867138, | |
| "grad_norm": 19.193851470947266, | |
| "learning_rate": 0.0002999936538534755, | |
| "loss": 1.8067, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.06893644921088371, | |
| "grad_norm": 25.025583267211914, | |
| "learning_rate": 0.0002999857213101595, | |
| "loss": 1.4576, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.07193368613309606, | |
| "grad_norm": 4.855524063110352, | |
| "learning_rate": 0.00029997461601054764, | |
| "loss": 1.0614, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0749309230553084, | |
| "grad_norm": 3.3954389095306396, | |
| "learning_rate": 0.00029996033821566326, | |
| "loss": 0.8964, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0749309230553084, | |
| "eval_loss": 1.0534682273864746, | |
| "eval_runtime": 0.2881, | |
| "eval_samples_per_second": 173.557, | |
| "eval_steps_per_second": 45.125, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07792815997752073, | |
| "grad_norm": 12.105545997619629, | |
| "learning_rate": 0.0002999428882610971, | |
| "loss": 3.0311, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.08092539689973306, | |
| "grad_norm": 3.334498882293701, | |
| "learning_rate": 0.00029992226655699945, | |
| "loss": 1.2946, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0839226338219454, | |
| "grad_norm": 2.8498733043670654, | |
| "learning_rate": 0.00029989847358807104, | |
| "loss": 1.1872, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.08691987074415773, | |
| "grad_norm": 2.367673873901367, | |
| "learning_rate": 0.0002998715099135508, | |
| "loss": 1.0292, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.08991710766637007, | |
| "grad_norm": 8.79304313659668, | |
| "learning_rate": 0.00029984137616720325, | |
| "loss": 1.2032, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0929143445885824, | |
| "grad_norm": 8.142653465270996, | |
| "learning_rate": 0.00029980807305730374, | |
| "loss": 1.2389, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.09591158151079474, | |
| "grad_norm": 4.5038628578186035, | |
| "learning_rate": 0.0002997716013666212, | |
| "loss": 1.0933, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.09890881843300707, | |
| "grad_norm": 2.439879894256592, | |
| "learning_rate": 0.0002997319619524003, | |
| "loss": 0.922, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1019060553552194, | |
| "grad_norm": 2.002732992172241, | |
| "learning_rate": 0.0002996891557463412, | |
| "loss": 0.8141, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.10490329227743174, | |
| "grad_norm": 1.9198921918869019, | |
| "learning_rate": 0.00029964318375457725, | |
| "loss": 0.5868, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.10790052919964407, | |
| "grad_norm": 1.1390972137451172, | |
| "learning_rate": 0.00029959404705765186, | |
| "loss": 0.4158, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.11089776612185641, | |
| "grad_norm": 0.9061455130577087, | |
| "learning_rate": 0.00029954174681049296, | |
| "loss": 0.3104, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.11389500304406874, | |
| "grad_norm": 3.6855151653289795, | |
| "learning_rate": 0.0002994862842423856, | |
| "loss": 1.3318, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.11689223996628108, | |
| "grad_norm": 2.992558717727661, | |
| "learning_rate": 0.00029942766065694333, | |
| "loss": 1.0331, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.11988947688849343, | |
| "grad_norm": 2.762493133544922, | |
| "learning_rate": 0.00029936587743207736, | |
| "loss": 0.7132, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12288671381070576, | |
| "grad_norm": 2.2291383743286133, | |
| "learning_rate": 0.00029930093601996446, | |
| "loss": 0.5774, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.12588395073291808, | |
| "grad_norm": 1.1489959955215454, | |
| "learning_rate": 0.0002992328379470125, | |
| "loss": 0.5567, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.12888118765513043, | |
| "grad_norm": 6.168476104736328, | |
| "learning_rate": 0.00029916158481382474, | |
| "loss": 0.6131, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.13187842457734275, | |
| "grad_norm": 5.408211708068848, | |
| "learning_rate": 0.0002990871782951623, | |
| "loss": 0.6638, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1348756614995551, | |
| "grad_norm": 1.5306873321533203, | |
| "learning_rate": 0.0002990096201399045, | |
| "loss": 0.5488, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.13787289842176742, | |
| "grad_norm": 1.8623676300048828, | |
| "learning_rate": 0.00029892891217100817, | |
| "loss": 0.4659, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.14087013534397977, | |
| "grad_norm": 1.6640721559524536, | |
| "learning_rate": 0.0002988450562854644, | |
| "loss": 0.4368, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.14386737226619212, | |
| "grad_norm": 0.3559802174568176, | |
| "learning_rate": 0.0002987580544542541, | |
| "loss": 0.0507, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.14686460918840444, | |
| "grad_norm": 0.4540441334247589, | |
| "learning_rate": 0.0002986679087223018, | |
| "loss": 0.087, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.1498618461106168, | |
| "grad_norm": 0.8076233267784119, | |
| "learning_rate": 0.00029857462120842744, | |
| "loss": 0.1023, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1498618461106168, | |
| "eval_loss": 0.3283706307411194, | |
| "eval_runtime": 0.2882, | |
| "eval_samples_per_second": 173.489, | |
| "eval_steps_per_second": 45.107, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1528590830328291, | |
| "grad_norm": 4.228235721588135, | |
| "learning_rate": 0.0002984781941052967, | |
| "loss": 1.0819, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.15585631995504146, | |
| "grad_norm": 3.424924612045288, | |
| "learning_rate": 0.0002983786296793692, | |
| "loss": 0.5749, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.15885355687725378, | |
| "grad_norm": 3.9904696941375732, | |
| "learning_rate": 0.00029827593027084546, | |
| "loss": 0.5831, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.16185079379946612, | |
| "grad_norm": 2.694119930267334, | |
| "learning_rate": 0.00029817009829361196, | |
| "loss": 0.4457, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.16484803072167845, | |
| "grad_norm": 1.2387803792953491, | |
| "learning_rate": 0.00029806113623518407, | |
| "loss": 0.3431, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.1678452676438908, | |
| "grad_norm": 1.6821039915084839, | |
| "learning_rate": 0.0002979490466566481, | |
| "loss": 0.3905, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.17084250456610311, | |
| "grad_norm": 0.6684949994087219, | |
| "learning_rate": 0.00029783383219260037, | |
| "loss": 0.3056, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.17383974148831546, | |
| "grad_norm": 0.7967026233673096, | |
| "learning_rate": 0.0002977154955510861, | |
| "loss": 0.3333, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.17683697841052778, | |
| "grad_norm": 0.5187807083129883, | |
| "learning_rate": 0.0002975940395135351, | |
| "loss": 0.2867, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.17983421533274013, | |
| "grad_norm": 7.2272138595581055, | |
| "learning_rate": 0.00029746946693469693, | |
| "loss": 1.0056, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.18283145225495245, | |
| "grad_norm": 8.9348726272583, | |
| "learning_rate": 0.00029734178074257325, | |
| "loss": 0.7786, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.1858286891771648, | |
| "grad_norm": 8.19704532623291, | |
| "learning_rate": 0.0002972109839383494, | |
| "loss": 0.3928, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.18882592609937715, | |
| "grad_norm": 4.3927483558654785, | |
| "learning_rate": 0.00029707707959632386, | |
| "loss": 0.7528, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.19182316302158947, | |
| "grad_norm": 2.271043539047241, | |
| "learning_rate": 0.0002969400708638358, | |
| "loss": 0.4877, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.19482039994380182, | |
| "grad_norm": 1.3864595890045166, | |
| "learning_rate": 0.000296799960961191, | |
| "loss": 0.2625, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.19781763686601414, | |
| "grad_norm": 2.2087323665618896, | |
| "learning_rate": 0.00029665675318158656, | |
| "loss": 0.2945, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.2008148737882265, | |
| "grad_norm": 3.766403913497925, | |
| "learning_rate": 0.00029651045089103316, | |
| "loss": 0.3807, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.2038121107104388, | |
| "grad_norm": 2.598832368850708, | |
| "learning_rate": 0.0002963610575282762, | |
| "loss": 0.3149, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.20680934763265116, | |
| "grad_norm": 0.677237331867218, | |
| "learning_rate": 0.0002962085766047146, | |
| "loss": 0.346, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.20980658455486348, | |
| "grad_norm": 0.5142577886581421, | |
| "learning_rate": 0.00029605301170431867, | |
| "loss": 0.2855, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.21280382147707583, | |
| "grad_norm": 0.5518949031829834, | |
| "learning_rate": 0.00029589436648354566, | |
| "loss": 0.3163, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.21580105839928815, | |
| "grad_norm": 0.336823046207428, | |
| "learning_rate": 0.00029573264467125377, | |
| "loss": 0.16, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.2187982953215005, | |
| "grad_norm": 0.2474360167980194, | |
| "learning_rate": 0.0002955678500686147, | |
| "loss": 0.0297, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.22179553224371282, | |
| "grad_norm": 0.18458165228366852, | |
| "learning_rate": 0.0002953999865490242, | |
| "loss": 0.0609, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.22479276916592517, | |
| "grad_norm": 0.36120983958244324, | |
| "learning_rate": 0.0002952290580580109, | |
| "loss": 0.0862, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.22479276916592517, | |
| "eval_loss": 0.16452732682228088, | |
| "eval_runtime": 0.2888, | |
| "eval_samples_per_second": 173.11, | |
| "eval_steps_per_second": 45.009, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.2277900060881375, | |
| "grad_norm": 1.3333512544631958, | |
| "learning_rate": 0.0002950550686131438, | |
| "loss": 0.6146, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.23078724301034984, | |
| "grad_norm": 1.2993559837341309, | |
| "learning_rate": 0.00029487802230393777, | |
| "loss": 0.2574, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.23378447993256216, | |
| "grad_norm": 1.2781016826629639, | |
| "learning_rate": 0.00029469792329175725, | |
| "loss": 0.2978, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.2367817168547745, | |
| "grad_norm": 5.145886421203613, | |
| "learning_rate": 0.0002945147758097187, | |
| "loss": 0.3251, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.23977895377698685, | |
| "grad_norm": 5.573575019836426, | |
| "learning_rate": 0.00029432858416259097, | |
| "loss": 0.3483, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.24277619069919917, | |
| "grad_norm": 2.6032469272613525, | |
| "learning_rate": 0.0002941393527266941, | |
| "loss": 0.306, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.24577342762141152, | |
| "grad_norm": 0.6271111965179443, | |
| "learning_rate": 0.00029394708594979657, | |
| "loss": 0.318, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.24877066454362384, | |
| "grad_norm": 0.5439050793647766, | |
| "learning_rate": 0.0002937517883510106, | |
| "loss": 0.2547, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.25176790146583616, | |
| "grad_norm": 0.5188155770301819, | |
| "learning_rate": 0.0002935534645206861, | |
| "loss": 0.2402, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.25476513838804854, | |
| "grad_norm": 1.3832889795303345, | |
| "learning_rate": 0.00029335211912030247, | |
| "loss": 0.147, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.25776237531026086, | |
| "grad_norm": 0.20522421598434448, | |
| "learning_rate": 0.0002931477568823596, | |
| "loss": 0.0365, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.2607596122324732, | |
| "grad_norm": 0.07317493855953217, | |
| "learning_rate": 0.00029294038261026595, | |
| "loss": 0.0178, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.2637568491546855, | |
| "grad_norm": 5.754029273986816, | |
| "learning_rate": 0.0002927300011782263, | |
| "loss": 0.5049, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.2667540860768979, | |
| "grad_norm": 1.9069617986679077, | |
| "learning_rate": 0.0002925166175311266, | |
| "loss": 0.297, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.2697513229991102, | |
| "grad_norm": 1.4803589582443237, | |
| "learning_rate": 0.0002923002366844182, | |
| "loss": 0.2419, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.2727485599213225, | |
| "grad_norm": 1.1726033687591553, | |
| "learning_rate": 0.0002920808637239998, | |
| "loss": 0.2449, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.27574579684353484, | |
| "grad_norm": 1.1483900547027588, | |
| "learning_rate": 0.00029185850380609757, | |
| "loss": 0.2845, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.2787430337657472, | |
| "grad_norm": 0.6498438715934753, | |
| "learning_rate": 0.00029163316215714477, | |
| "loss": 0.3168, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.28174027068795954, | |
| "grad_norm": 3.8744821548461914, | |
| "learning_rate": 0.00029140484407365807, | |
| "loss": 0.3098, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.28473750761017186, | |
| "grad_norm": 5.238924026489258, | |
| "learning_rate": 0.00029117355492211345, | |
| "loss": 0.3747, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.28773474453238423, | |
| "grad_norm": 4.835148334503174, | |
| "learning_rate": 0.0002909393001388201, | |
| "loss": 0.311, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.29073198145459656, | |
| "grad_norm": 3.1126749515533447, | |
| "learning_rate": 0.00029070208522979246, | |
| "loss": 0.1933, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.2937292183768089, | |
| "grad_norm": 0.31741341948509216, | |
| "learning_rate": 0.000290461915770621, | |
| "loss": 0.0311, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.2967264552990212, | |
| "grad_norm": 0.13816803693771362, | |
| "learning_rate": 0.00029021879740634106, | |
| "loss": 0.0489, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.2997236922212336, | |
| "grad_norm": 0.16050726175308228, | |
| "learning_rate": 0.0002899727358513002, | |
| "loss": 0.0421, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2997236922212336, | |
| "eval_loss": 0.14205443859100342, | |
| "eval_runtime": 0.2881, | |
| "eval_samples_per_second": 173.58, | |
| "eval_steps_per_second": 45.131, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3027209291434459, | |
| "grad_norm": 4.475709438323975, | |
| "learning_rate": 0.0002897237368890237, | |
| "loss": 0.7248, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.3057181660656582, | |
| "grad_norm": 1.3565483093261719, | |
| "learning_rate": 0.00028947180637207894, | |
| "loss": 0.2832, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.30871540298787054, | |
| "grad_norm": 1.5489473342895508, | |
| "learning_rate": 0.0002892169502219377, | |
| "loss": 0.3576, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.3117126399100829, | |
| "grad_norm": 1.2731544971466064, | |
| "learning_rate": 0.00028895917442883697, | |
| "loss": 0.2847, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.31470987683229523, | |
| "grad_norm": 0.5488539934158325, | |
| "learning_rate": 0.000288698485051638, | |
| "loss": 0.2249, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.31770711375450755, | |
| "grad_norm": 0.6603264808654785, | |
| "learning_rate": 0.0002884348882176842, | |
| "loss": 0.2748, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.3207043506767199, | |
| "grad_norm": 1.190644383430481, | |
| "learning_rate": 0.0002881683901226569, | |
| "loss": 0.264, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.32370158759893225, | |
| "grad_norm": 3.849586248397827, | |
| "learning_rate": 0.00028789899703042976, | |
| "loss": 0.2899, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.32669882452114457, | |
| "grad_norm": 2.8036534786224365, | |
| "learning_rate": 0.00028762671527292165, | |
| "loss": 0.2266, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.3296960614433569, | |
| "grad_norm": 1.1855659484863281, | |
| "learning_rate": 0.00028735155124994774, | |
| "loss": 0.1432, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.33269329836556927, | |
| "grad_norm": 0.14694784581661224, | |
| "learning_rate": 0.0002870735114290689, | |
| "loss": 0.0225, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.3356905352877816, | |
| "grad_norm": 0.08722022920846939, | |
| "learning_rate": 0.0002867926023454401, | |
| "loss": 0.0243, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.3386877722099939, | |
| "grad_norm": 1.4064624309539795, | |
| "learning_rate": 0.00028650883060165634, | |
| "loss": 0.4202, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.34168500913220623, | |
| "grad_norm": 1.0942851305007935, | |
| "learning_rate": 0.00028622220286759787, | |
| "loss": 0.2193, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.3446822460544186, | |
| "grad_norm": 1.4071762561798096, | |
| "learning_rate": 0.0002859327258802732, | |
| "loss": 0.2772, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.3476794829766309, | |
| "grad_norm": 1.451495885848999, | |
| "learning_rate": 0.0002856404064436606, | |
| "loss": 0.3247, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.35067671989884325, | |
| "grad_norm": 0.8838515281677246, | |
| "learning_rate": 0.0002853452514285487, | |
| "loss": 0.2307, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.35367395682105557, | |
| "grad_norm": 0.43812039494514465, | |
| "learning_rate": 0.0002850472677723743, | |
| "loss": 0.2225, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.35667119374326794, | |
| "grad_norm": 1.919777274131775, | |
| "learning_rate": 0.0002847464624790599, | |
| "loss": 0.2529, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.35966843066548027, | |
| "grad_norm": 3.364579916000366, | |
| "learning_rate": 0.00028444284261884876, | |
| "loss": 0.2957, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3626656675876926, | |
| "grad_norm": 3.1780946254730225, | |
| "learning_rate": 0.0002841364153281389, | |
| "loss": 0.2983, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.3656629045099049, | |
| "grad_norm": 1.9313762187957764, | |
| "learning_rate": 0.000283827187809315, | |
| "loss": 0.1741, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.3686601414321173, | |
| "grad_norm": 0.2901758849620819, | |
| "learning_rate": 0.0002835151673305797, | |
| "loss": 0.0191, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.3716573783543296, | |
| "grad_norm": 0.18410703539848328, | |
| "learning_rate": 0.00028320036122578225, | |
| "loss": 0.0579, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.3746546152765419, | |
| "grad_norm": 0.06442587822675705, | |
| "learning_rate": 0.0002828827768942464, | |
| "loss": 0.0401, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.3746546152765419, | |
| "eval_loss": 0.12974713742733002, | |
| "eval_runtime": 0.2912, | |
| "eval_samples_per_second": 171.727, | |
| "eval_steps_per_second": 44.649, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.3776518521987543, | |
| "grad_norm": 5.953274726867676, | |
| "learning_rate": 0.00028256242180059644, | |
| "loss": 0.5857, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.3806490891209666, | |
| "grad_norm": 1.0578787326812744, | |
| "learning_rate": 0.0002822393034745815, | |
| "loss": 0.1907, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.38364632604317894, | |
| "grad_norm": 1.2669620513916016, | |
| "learning_rate": 0.0002819134295108992, | |
| "loss": 0.2632, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.38664356296539126, | |
| "grad_norm": 1.2083393335342407, | |
| "learning_rate": 0.0002815848075690163, | |
| "loss": 0.2581, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.38964079988760364, | |
| "grad_norm": 0.6875675916671753, | |
| "learning_rate": 0.00028125344537298933, | |
| "loss": 0.2141, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.39263803680981596, | |
| "grad_norm": 0.6001489162445068, | |
| "learning_rate": 0.00028091935071128274, | |
| "loss": 0.2624, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.3956352737320283, | |
| "grad_norm": 0.28877830505371094, | |
| "learning_rate": 0.00028058253143658596, | |
| "loss": 0.2115, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.3986325106542406, | |
| "grad_norm": 0.8344032168388367, | |
| "learning_rate": 0.0002802429954656287, | |
| "loss": 0.234, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.401629747576453, | |
| "grad_norm": 2.311697244644165, | |
| "learning_rate": 0.00027990075077899494, | |
| "loss": 0.173, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.4046269844986653, | |
| "grad_norm": 0.9839431643486023, | |
| "learning_rate": 0.0002795558054209354, | |
| "loss": 0.0744, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.4076242214208776, | |
| "grad_norm": 0.23247428238391876, | |
| "learning_rate": 0.0002792081674991785, | |
| "loss": 0.0324, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.41062145834308994, | |
| "grad_norm": 0.11418312788009644, | |
| "learning_rate": 0.00027885784518473955, | |
| "loss": 0.0338, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.4136186952653023, | |
| "grad_norm": 2.2888922691345215, | |
| "learning_rate": 0.0002785048467117289, | |
| "loss": 0.3951, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.41661593218751464, | |
| "grad_norm": 1.3474727869033813, | |
| "learning_rate": 0.00027814918037715846, | |
| "loss": 0.2827, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.41961316910972696, | |
| "grad_norm": 0.958093523979187, | |
| "learning_rate": 0.0002777908545407464, | |
| "loss": 0.2105, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.4226104060319393, | |
| "grad_norm": 1.1106938123703003, | |
| "learning_rate": 0.00027742987762472104, | |
| "loss": 0.2451, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.42560764295415165, | |
| "grad_norm": 0.991568386554718, | |
| "learning_rate": 0.0002770662581136226, | |
| "loss": 0.2107, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.428604879876364, | |
| "grad_norm": 0.7932851314544678, | |
| "learning_rate": 0.0002767000045541039, | |
| "loss": 0.2097, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.4316021167985763, | |
| "grad_norm": 0.4382745623588562, | |
| "learning_rate": 0.0002763311255547294, | |
| "loss": 0.2098, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.4345993537207887, | |
| "grad_norm": 0.4467020034790039, | |
| "learning_rate": 0.0002759596297857729, | |
| "loss": 0.2249, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.437596590643001, | |
| "grad_norm": 0.7452898025512695, | |
| "learning_rate": 0.0002755855259790139, | |
| "loss": 0.2022, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.4405938275652133, | |
| "grad_norm": 0.8051543831825256, | |
| "learning_rate": 0.000275208822927532, | |
| "loss": 0.2018, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.44359106448742563, | |
| "grad_norm": 0.4602643847465515, | |
| "learning_rate": 0.00027482952948550056, | |
| "loss": 0.0265, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.446588301409638, | |
| "grad_norm": 0.16789375245571136, | |
| "learning_rate": 0.00027444765456797863, | |
| "loss": 0.0358, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.44958553833185033, | |
| "grad_norm": 0.2375824749469757, | |
| "learning_rate": 0.000274063207150701, | |
| "loss": 0.0459, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.44958553833185033, | |
| "eval_loss": 0.26043474674224854, | |
| "eval_runtime": 0.2878, | |
| "eval_samples_per_second": 173.721, | |
| "eval_steps_per_second": 45.167, | |
| "step": 150 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 668, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.90057513051095e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |