| { | |
| "best_metric": 0.12361826002597809, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-100", | |
| "epoch": 0.253324889170361, | |
| "eval_steps": 50, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00253324889170361, | |
| "grad_norm": 3.6676442623138428, | |
| "learning_rate": 4e-05, | |
| "loss": 3.0591, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00253324889170361, | |
| "eval_loss": 3.577761650085449, | |
| "eval_runtime": 44.9583, | |
| "eval_samples_per_second": 3.715, | |
| "eval_steps_per_second": 1.868, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00506649778340722, | |
| "grad_norm": 3.199979305267334, | |
| "learning_rate": 8e-05, | |
| "loss": 2.7215, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007599746675110829, | |
| "grad_norm": 3.33293080329895, | |
| "learning_rate": 0.00012, | |
| "loss": 2.9505, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01013299556681444, | |
| "grad_norm": 4.012212753295898, | |
| "learning_rate": 0.00016, | |
| "loss": 2.8184, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01266624445851805, | |
| "grad_norm": 4.058014869689941, | |
| "learning_rate": 0.0002, | |
| "loss": 1.986, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.015199493350221659, | |
| "grad_norm": 3.3792548179626465, | |
| "learning_rate": 0.00019994532573409262, | |
| "loss": 1.3189, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01773274224192527, | |
| "grad_norm": 3.53857159614563, | |
| "learning_rate": 0.00019978136272187747, | |
| "loss": 0.7923, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02026599113362888, | |
| "grad_norm": 5.587308406829834, | |
| "learning_rate": 0.00019950829025450114, | |
| "loss": 0.7796, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.022799240025332488, | |
| "grad_norm": 3.04203724861145, | |
| "learning_rate": 0.00019912640693269752, | |
| "loss": 0.1713, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0253324889170361, | |
| "grad_norm": 3.9056479930877686, | |
| "learning_rate": 0.00019863613034027224, | |
| "loss": 0.223, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02786573780873971, | |
| "grad_norm": 3.32242488861084, | |
| "learning_rate": 0.00019803799658748094, | |
| "loss": 0.256, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.030398986700443317, | |
| "grad_norm": 0.5264054536819458, | |
| "learning_rate": 0.0001973326597248006, | |
| "loss": 0.0183, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.032932235592146926, | |
| "grad_norm": 2.039252281188965, | |
| "learning_rate": 0.00019652089102773488, | |
| "loss": 0.2864, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03546548448385054, | |
| "grad_norm": 1.891056776046753, | |
| "learning_rate": 0.00019560357815343577, | |
| "loss": 0.0422, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03799873337555415, | |
| "grad_norm": 2.2989518642425537, | |
| "learning_rate": 0.00019458172417006347, | |
| "loss": 0.5805, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04053198226725776, | |
| "grad_norm": 2.4155068397521973, | |
| "learning_rate": 0.0001934564464599461, | |
| "loss": 0.2322, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04306523115896137, | |
| "grad_norm": 2.4074628353118896, | |
| "learning_rate": 0.00019222897549773848, | |
| "loss": 0.4752, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.045598480050664976, | |
| "grad_norm": 0.9219037294387817, | |
| "learning_rate": 0.00019090065350491626, | |
| "loss": 0.2356, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.048131728942368585, | |
| "grad_norm": 1.37091064453125, | |
| "learning_rate": 0.00018947293298207635, | |
| "loss": 0.2088, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0506649778340722, | |
| "grad_norm": 0.2628805935382843, | |
| "learning_rate": 0.0001879473751206489, | |
| "loss": 0.0109, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05319822672577581, | |
| "grad_norm": 2.158172845840454, | |
| "learning_rate": 0.00018632564809575742, | |
| "loss": 0.2097, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05573147561747942, | |
| "grad_norm": 1.4831571578979492, | |
| "learning_rate": 0.00018460952524209355, | |
| "loss": 0.1739, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.058264724509183026, | |
| "grad_norm": 1.6883933544158936, | |
| "learning_rate": 0.00018280088311480201, | |
| "loss": 0.2868, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.060797973400886635, | |
| "grad_norm": 1.1558237075805664, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.1405, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06333122229259025, | |
| "grad_norm": 1.421405553817749, | |
| "learning_rate": 0.00017891405093963938, | |
| "loss": 0.162, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06586447118429385, | |
| "grad_norm": 3.7727131843566895, | |
| "learning_rate": 0.00017684011108568592, | |
| "loss": 0.291, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.06839772007599747, | |
| "grad_norm": 1.3770571947097778, | |
| "learning_rate": 0.0001746821476984154, | |
| "loss": 0.12, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07093096896770108, | |
| "grad_norm": 6.9208149909973145, | |
| "learning_rate": 0.00017244252047910892, | |
| "loss": 0.7353, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.07346421785940468, | |
| "grad_norm": 2.6051218509674072, | |
| "learning_rate": 0.00017012367842724887, | |
| "loss": 0.2355, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0759974667511083, | |
| "grad_norm": 3.3124608993530273, | |
| "learning_rate": 0.00016772815716257412, | |
| "loss": 0.7072, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0785307156428119, | |
| "grad_norm": 2.073368787765503, | |
| "learning_rate": 0.00016525857615241687, | |
| "loss": 0.1301, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.08106396453451552, | |
| "grad_norm": 0.6973274350166321, | |
| "learning_rate": 0.0001627176358473537, | |
| "loss": 0.0637, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.08359721342621912, | |
| "grad_norm": 1.706817865371704, | |
| "learning_rate": 0.00016010811472830252, | |
| "loss": 0.125, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08613046231792273, | |
| "grad_norm": 1.9682927131652832, | |
| "learning_rate": 0.00015743286626829437, | |
| "loss": 0.3533, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.08866371120962635, | |
| "grad_norm": 2.4648215770721436, | |
| "learning_rate": 0.00015469481581224272, | |
| "loss": 0.6709, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.09119696010132995, | |
| "grad_norm": 2.308652877807617, | |
| "learning_rate": 0.00015189695737812152, | |
| "loss": 0.1397, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09373020899303357, | |
| "grad_norm": 3.2563140392303467, | |
| "learning_rate": 0.00014904235038305083, | |
| "loss": 0.3003, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.09626345788473717, | |
| "grad_norm": 3.14212965965271, | |
| "learning_rate": 0.0001461341162978688, | |
| "loss": 0.2907, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.09879670677644078, | |
| "grad_norm": 1.726691484451294, | |
| "learning_rate": 0.00014317543523384928, | |
| "loss": 0.0962, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1013299556681444, | |
| "grad_norm": 4.3779449462890625, | |
| "learning_rate": 0.00014016954246529696, | |
| "loss": 0.3433, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.103863204559848, | |
| "grad_norm": 3.401987314224243, | |
| "learning_rate": 0.00013711972489182208, | |
| "loss": 0.2321, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.10639645345155162, | |
| "grad_norm": 1.7866804599761963, | |
| "learning_rate": 0.00013402931744416433, | |
| "loss": 0.0461, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.10892970234325522, | |
| "grad_norm": 2.7210962772369385, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.2669, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.11146295123495883, | |
| "grad_norm": 0.31108513474464417, | |
| "learning_rate": 0.00012774029087618446, | |
| "loss": 0.0179, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.11399620012666245, | |
| "grad_norm": 1.0655226707458496, | |
| "learning_rate": 0.00012454854871407994, | |
| "loss": 0.1818, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.11652944901836605, | |
| "grad_norm": 2.1581103801727295, | |
| "learning_rate": 0.0001213299630743747, | |
| "loss": 0.4705, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.11906269791006967, | |
| "grad_norm": 0.13762931525707245, | |
| "learning_rate": 0.000118088053433211, | |
| "loss": 0.0066, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.12159594680177327, | |
| "grad_norm": 0.04102027043700218, | |
| "learning_rate": 0.0001148263647711842, | |
| "loss": 0.0021, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.12412919569347688, | |
| "grad_norm": 0.09145709127187729, | |
| "learning_rate": 0.00011154846369695863, | |
| "loss": 0.0054, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.1266624445851805, | |
| "grad_norm": 0.6207671165466309, | |
| "learning_rate": 0.00010825793454723325, | |
| "loss": 0.009, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1266624445851805, | |
| "eval_loss": 0.13963158428668976, | |
| "eval_runtime": 45.5826, | |
| "eval_samples_per_second": 3.664, | |
| "eval_steps_per_second": 1.843, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12919569347688412, | |
| "grad_norm": 4.131649494171143, | |
| "learning_rate": 0.00010495837546732224, | |
| "loss": 0.0664, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.1317289423685877, | |
| "grad_norm": 1.5766167640686035, | |
| "learning_rate": 0.00010165339447663587, | |
| "loss": 0.0462, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.13426219126029132, | |
| "grad_norm": 0.21246828138828278, | |
| "learning_rate": 9.834660552336415e-05, | |
| "loss": 0.017, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.13679544015199493, | |
| "grad_norm": 0.4235173761844635, | |
| "learning_rate": 9.504162453267777e-05, | |
| "loss": 0.0497, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.13932868904369855, | |
| "grad_norm": 1.9022583961486816, | |
| "learning_rate": 9.174206545276677e-05, | |
| "loss": 0.1731, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.14186193793540217, | |
| "grad_norm": 0.0696033164858818, | |
| "learning_rate": 8.845153630304139e-05, | |
| "loss": 0.0074, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.14439518682710575, | |
| "grad_norm": 0.38361629843711853, | |
| "learning_rate": 8.517363522881579e-05, | |
| "loss": 0.0308, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.14692843571880937, | |
| "grad_norm": 0.0552719309926033, | |
| "learning_rate": 8.191194656678904e-05, | |
| "loss": 0.0051, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.14946168461051298, | |
| "grad_norm": 0.4546244144439697, | |
| "learning_rate": 7.867003692562534e-05, | |
| "loss": 0.0815, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.1519949335022166, | |
| "grad_norm": 1.4817312955856323, | |
| "learning_rate": 7.54514512859201e-05, | |
| "loss": 0.0728, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.15452818239392022, | |
| "grad_norm": 0.29890382289886475, | |
| "learning_rate": 7.225970912381556e-05, | |
| "loss": 0.023, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.1570614312856238, | |
| "grad_norm": 0.16949699819087982, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.0116, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.15959468017732742, | |
| "grad_norm": 0.6186251044273376, | |
| "learning_rate": 6.59706825558357e-05, | |
| "loss": 0.1467, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.16212792906903103, | |
| "grad_norm": 0.24091556668281555, | |
| "learning_rate": 6.28802751081779e-05, | |
| "loss": 0.0387, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.16466117796073465, | |
| "grad_norm": 0.2896825969219208, | |
| "learning_rate": 5.983045753470308e-05, | |
| "loss": 0.0173, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.16719442685243824, | |
| "grad_norm": 0.030425388365983963, | |
| "learning_rate": 5.6824564766150726e-05, | |
| "loss": 0.0029, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.16972767574414185, | |
| "grad_norm": 0.41832366585731506, | |
| "learning_rate": 5.386588370213124e-05, | |
| "loss": 0.0403, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.17226092463584547, | |
| "grad_norm": 1.3154964447021484, | |
| "learning_rate": 5.095764961694922e-05, | |
| "loss": 0.2766, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.17479417352754908, | |
| "grad_norm": 1.726725459098816, | |
| "learning_rate": 4.810304262187852e-05, | |
| "loss": 0.4326, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.1773274224192527, | |
| "grad_norm": 0.03612220287322998, | |
| "learning_rate": 4.530518418775733e-05, | |
| "loss": 0.0035, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.1798606713109563, | |
| "grad_norm": 0.5889875292778015, | |
| "learning_rate": 4.256713373170564e-05, | |
| "loss": 0.1592, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.1823939202026599, | |
| "grad_norm": 1.068608283996582, | |
| "learning_rate": 3.9891885271697496e-05, | |
| "loss": 0.2189, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.18492716909436352, | |
| "grad_norm": 0.20104023814201355, | |
| "learning_rate": 3.7282364152646297e-05, | |
| "loss": 0.0261, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.18746041798606713, | |
| "grad_norm": 0.7733007073402405, | |
| "learning_rate": 3.4741423847583134e-05, | |
| "loss": 0.1253, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.18999366687777075, | |
| "grad_norm": 1.527602195739746, | |
| "learning_rate": 3.227184283742591e-05, | |
| "loss": 0.1233, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.19252691576947434, | |
| "grad_norm": 0.035904768854379654, | |
| "learning_rate": 2.9876321572751144e-05, | |
| "loss": 0.0033, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.19506016466117795, | |
| "grad_norm": 1.0097168684005737, | |
| "learning_rate": 2.7557479520891104e-05, | |
| "loss": 0.1862, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.19759341355288157, | |
| "grad_norm": 0.6764742732048035, | |
| "learning_rate": 2.5317852301584643e-05, | |
| "loss": 0.1849, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.20012666244458518, | |
| "grad_norm": 0.2706001102924347, | |
| "learning_rate": 2.315988891431412e-05, | |
| "loss": 0.018, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.2026599113362888, | |
| "grad_norm": 0.06733691692352295, | |
| "learning_rate": 2.1085949060360654e-05, | |
| "loss": 0.0067, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.2051931602279924, | |
| "grad_norm": 0.09681247174739838, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.0049, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.207726409119696, | |
| "grad_norm": 0.052867814898490906, | |
| "learning_rate": 1.7199116885197995e-05, | |
| "loss": 0.0051, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.21025965801139962, | |
| "grad_norm": 0.16184115409851074, | |
| "learning_rate": 1.5390474757906446e-05, | |
| "loss": 0.0129, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.21279290690310323, | |
| "grad_norm": 1.406388759613037, | |
| "learning_rate": 1.3674351904242611e-05, | |
| "loss": 0.1817, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.21532615579480685, | |
| "grad_norm": 0.08576802909374237, | |
| "learning_rate": 1.2052624879351104e-05, | |
| "loss": 0.007, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.21785940468651044, | |
| "grad_norm": 1.425647497177124, | |
| "learning_rate": 1.0527067017923654e-05, | |
| "loss": 0.1835, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.22039265357821405, | |
| "grad_norm": 0.06112959608435631, | |
| "learning_rate": 9.09934649508375e-06, | |
| "loss": 0.0061, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.22292590246991767, | |
| "grad_norm": 0.14833374321460724, | |
| "learning_rate": 7.771024502261526e-06, | |
| "loss": 0.0081, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.22545915136162129, | |
| "grad_norm": 0.27038395404815674, | |
| "learning_rate": 6.543553540053926e-06, | |
| "loss": 0.0451, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.2279924002533249, | |
| "grad_norm": 0.3804483115673065, | |
| "learning_rate": 5.418275829936537e-06, | |
| "loss": 0.0779, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.2305256491450285, | |
| "grad_norm": 0.04810729995369911, | |
| "learning_rate": 4.3964218465642355e-06, | |
| "loss": 0.0033, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.2330588980367321, | |
| "grad_norm": 0.12134478241205215, | |
| "learning_rate": 3.4791089722651436e-06, | |
| "loss": 0.0067, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.23559214692843572, | |
| "grad_norm": 1.7594163417816162, | |
| "learning_rate": 2.667340275199426e-06, | |
| "loss": 0.0616, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.23812539582013934, | |
| "grad_norm": 1.7588186264038086, | |
| "learning_rate": 1.9620034125190644e-06, | |
| "loss": 0.2098, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.24065864471184295, | |
| "grad_norm": 0.091976098716259, | |
| "learning_rate": 1.3638696597277679e-06, | |
| "loss": 0.0068, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.24319189360354654, | |
| "grad_norm": 0.14842090010643005, | |
| "learning_rate": 8.735930673024806e-07, | |
| "loss": 0.0052, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.24572514249525015, | |
| "grad_norm": 0.11459323018789291, | |
| "learning_rate": 4.917097454988584e-07, | |
| "loss": 0.0039, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.24825839138695377, | |
| "grad_norm": 0.2080399990081787, | |
| "learning_rate": 2.1863727812254653e-07, | |
| "loss": 0.007, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.25079164027865736, | |
| "grad_norm": 0.6975619792938232, | |
| "learning_rate": 5.467426590739511e-08, | |
| "loss": 0.0261, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.253324889170361, | |
| "grad_norm": 0.08974107354879379, | |
| "learning_rate": 0.0, | |
| "loss": 0.0033, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.253324889170361, | |
| "eval_loss": 0.12361826002597809, | |
| "eval_runtime": 45.5565, | |
| "eval_samples_per_second": 3.666, | |
| "eval_steps_per_second": 1.844, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.32218823376896e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |