| { | |
| "best_metric": 0.34765490889549255, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-100", | |
| "epoch": 0.0020115563914689895, | |
| "eval_steps": 25, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.0115563914689893e-05, | |
| "grad_norm": 0.29655277729034424, | |
| "learning_rate": 4e-05, | |
| "loss": 0.4437, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.0115563914689893e-05, | |
| "eval_loss": 1.1714186668395996, | |
| "eval_runtime": 7328.1947, | |
| "eval_samples_per_second": 2.856, | |
| "eval_steps_per_second": 1.428, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.023112782937979e-05, | |
| "grad_norm": 0.5731308460235596, | |
| "learning_rate": 8e-05, | |
| "loss": 0.3697, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 6.034669174406968e-05, | |
| "grad_norm": 0.6497276425361633, | |
| "learning_rate": 0.00012, | |
| "loss": 0.4203, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 8.046225565875957e-05, | |
| "grad_norm": 0.9947681427001953, | |
| "learning_rate": 0.00016, | |
| "loss": 0.5204, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00010057781957344947, | |
| "grad_norm": 0.7415378093719482, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4131, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00012069338348813936, | |
| "grad_norm": 0.8263693451881409, | |
| "learning_rate": 0.00019994532573409262, | |
| "loss": 0.5349, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00014080894740282925, | |
| "grad_norm": 0.8251563310623169, | |
| "learning_rate": 0.00019978136272187747, | |
| "loss": 0.1855, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00016092451131751915, | |
| "grad_norm": 0.7272641658782959, | |
| "learning_rate": 0.00019950829025450114, | |
| "loss": 0.1285, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00018104007523220904, | |
| "grad_norm": 0.6202177405357361, | |
| "learning_rate": 0.00019912640693269752, | |
| "loss": 0.1598, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00020115563914689893, | |
| "grad_norm": 1.1333729028701782, | |
| "learning_rate": 0.00019863613034027224, | |
| "loss": 0.3572, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00022127120306158883, | |
| "grad_norm": 0.8228061199188232, | |
| "learning_rate": 0.00019803799658748094, | |
| "loss": 0.2095, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00024138676697627872, | |
| "grad_norm": 2.149914026260376, | |
| "learning_rate": 0.0001973326597248006, | |
| "loss": 0.4364, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00026150233089096864, | |
| "grad_norm": 0.8230195045471191, | |
| "learning_rate": 0.00019652089102773488, | |
| "loss": 0.233, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0002816178948056585, | |
| "grad_norm": 1.5093271732330322, | |
| "learning_rate": 0.00019560357815343577, | |
| "loss": 0.4418, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.00030173345872034843, | |
| "grad_norm": 0.5346623063087463, | |
| "learning_rate": 0.00019458172417006347, | |
| "loss": 0.1451, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0003218490226350383, | |
| "grad_norm": 0.546474039554596, | |
| "learning_rate": 0.0001934564464599461, | |
| "loss": 0.1511, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0003419645865497282, | |
| "grad_norm": 0.7137768268585205, | |
| "learning_rate": 0.00019222897549773848, | |
| "loss": 0.1932, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0003620801504644181, | |
| "grad_norm": 1.1197693347930908, | |
| "learning_rate": 0.00019090065350491626, | |
| "loss": 0.34, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.000382195714379108, | |
| "grad_norm": 1.2347760200500488, | |
| "learning_rate": 0.00018947293298207635, | |
| "loss": 0.2232, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.00040231127829379787, | |
| "grad_norm": 0.9798358082771301, | |
| "learning_rate": 0.0001879473751206489, | |
| "loss": 0.2199, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0004224268422084878, | |
| "grad_norm": 1.1938731670379639, | |
| "learning_rate": 0.00018632564809575742, | |
| "loss": 0.3553, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00044254240612317766, | |
| "grad_norm": 1.013114094734192, | |
| "learning_rate": 0.00018460952524209355, | |
| "loss": 0.2323, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0004626579700378676, | |
| "grad_norm": 0.8954797387123108, | |
| "learning_rate": 0.00018280088311480201, | |
| "loss": 0.1924, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.00048277353395255744, | |
| "grad_norm": 1.2280372381210327, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.3561, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0005028890978672474, | |
| "grad_norm": 0.9228379726409912, | |
| "learning_rate": 0.00017891405093963938, | |
| "loss": 0.331, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0005028890978672474, | |
| "eval_loss": 0.38219088315963745, | |
| "eval_runtime": 7333.2365, | |
| "eval_samples_per_second": 2.854, | |
| "eval_steps_per_second": 1.427, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0005230046617819373, | |
| "grad_norm": 1.3667868375778198, | |
| "learning_rate": 0.00017684011108568592, | |
| "loss": 0.3585, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0005431202256966271, | |
| "grad_norm": 0.8309668898582458, | |
| "learning_rate": 0.0001746821476984154, | |
| "loss": 0.2539, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.000563235789611317, | |
| "grad_norm": 0.8600310683250427, | |
| "learning_rate": 0.00017244252047910892, | |
| "loss": 0.4283, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0005833513535260069, | |
| "grad_norm": 1.5213987827301025, | |
| "learning_rate": 0.00017012367842724887, | |
| "loss": 0.5058, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0006034669174406969, | |
| "grad_norm": 1.0365674495697021, | |
| "learning_rate": 0.00016772815716257412, | |
| "loss": 0.439, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0006235824813553867, | |
| "grad_norm": 1.1248812675476074, | |
| "learning_rate": 0.00016525857615241687, | |
| "loss": 0.1794, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0006436980452700766, | |
| "grad_norm": 2.210256576538086, | |
| "learning_rate": 0.0001627176358473537, | |
| "loss": 0.7656, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0006638136091847665, | |
| "grad_norm": 1.926735758781433, | |
| "learning_rate": 0.00016010811472830252, | |
| "loss": 0.5577, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0006839291730994564, | |
| "grad_norm": 2.0872886180877686, | |
| "learning_rate": 0.00015743286626829437, | |
| "loss": 0.2975, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0007040447370141462, | |
| "grad_norm": 1.9924815893173218, | |
| "learning_rate": 0.00015469481581224272, | |
| "loss": 0.5404, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0007241603009288362, | |
| "grad_norm": 0.763292670249939, | |
| "learning_rate": 0.00015189695737812152, | |
| "loss": 0.2239, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0007442758648435261, | |
| "grad_norm": 1.0943641662597656, | |
| "learning_rate": 0.00014904235038305083, | |
| "loss": 0.1645, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.000764391428758216, | |
| "grad_norm": 1.2765237092971802, | |
| "learning_rate": 0.0001461341162978688, | |
| "loss": 0.2827, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0007845069926729058, | |
| "grad_norm": 0.7692890763282776, | |
| "learning_rate": 0.00014317543523384928, | |
| "loss": 0.1748, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0008046225565875957, | |
| "grad_norm": 0.8414583206176758, | |
| "learning_rate": 0.00014016954246529696, | |
| "loss": 0.2124, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0008247381205022857, | |
| "grad_norm": 1.9153568744659424, | |
| "learning_rate": 0.00013711972489182208, | |
| "loss": 0.8024, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0008448536844169756, | |
| "grad_norm": 1.7804728746414185, | |
| "learning_rate": 0.00013402931744416433, | |
| "loss": 0.3997, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0008649692483316654, | |
| "grad_norm": 1.816100835800171, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.6297, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0008850848122463553, | |
| "grad_norm": 0.5582104921340942, | |
| "learning_rate": 0.00012774029087618446, | |
| "loss": 0.1037, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0009052003761610452, | |
| "grad_norm": 1.3087366819381714, | |
| "learning_rate": 0.00012454854871407994, | |
| "loss": 0.3838, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0009253159400757352, | |
| "grad_norm": 1.9638283252716064, | |
| "learning_rate": 0.0001213299630743747, | |
| "loss": 0.5667, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.000945431503990425, | |
| "grad_norm": 1.8329553604125977, | |
| "learning_rate": 0.000118088053433211, | |
| "loss": 0.5189, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0009655470679051149, | |
| "grad_norm": 1.815300464630127, | |
| "learning_rate": 0.0001148263647711842, | |
| "loss": 0.5543, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0009856626318198048, | |
| "grad_norm": 2.2588958740234375, | |
| "learning_rate": 0.00011154846369695863, | |
| "loss": 0.3947, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0010057781957344947, | |
| "grad_norm": 2.2676048278808594, | |
| "learning_rate": 0.00010825793454723325, | |
| "loss": 0.6438, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0010057781957344947, | |
| "eval_loss": 0.3769894242286682, | |
| "eval_runtime": 7329.2477, | |
| "eval_samples_per_second": 2.856, | |
| "eval_steps_per_second": 1.428, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0010258937596491846, | |
| "grad_norm": 0.3635750710964203, | |
| "learning_rate": 0.00010495837546732224, | |
| "loss": 0.2263, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.0010460093235638746, | |
| "grad_norm": 0.3851054906845093, | |
| "learning_rate": 0.00010165339447663587, | |
| "loss": 0.1225, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.0010661248874785643, | |
| "grad_norm": 1.072131872177124, | |
| "learning_rate": 9.834660552336415e-05, | |
| "loss": 0.4456, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.0010862404513932542, | |
| "grad_norm": 0.7393021583557129, | |
| "learning_rate": 9.504162453267777e-05, | |
| "loss": 0.3782, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.0011063560153079441, | |
| "grad_norm": 0.5794671177864075, | |
| "learning_rate": 9.174206545276677e-05, | |
| "loss": 0.2947, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.001126471579222634, | |
| "grad_norm": 0.6361809372901917, | |
| "learning_rate": 8.845153630304139e-05, | |
| "loss": 0.1859, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.001146587143137324, | |
| "grad_norm": 0.8540146946907043, | |
| "learning_rate": 8.517363522881579e-05, | |
| "loss": 0.3623, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.0011667027070520139, | |
| "grad_norm": 0.6807648539543152, | |
| "learning_rate": 8.191194656678904e-05, | |
| "loss": 0.2334, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.0011868182709667038, | |
| "grad_norm": 0.8112823963165283, | |
| "learning_rate": 7.867003692562534e-05, | |
| "loss": 0.4587, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.0012069338348813937, | |
| "grad_norm": 0.7327591776847839, | |
| "learning_rate": 7.54514512859201e-05, | |
| "loss": 0.3364, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0012270493987960834, | |
| "grad_norm": 0.8124757409095764, | |
| "learning_rate": 7.225970912381556e-05, | |
| "loss": 0.3287, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.0012471649627107733, | |
| "grad_norm": 0.8952487707138062, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.3561, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.0012672805266254633, | |
| "grad_norm": 0.7453446388244629, | |
| "learning_rate": 6.59706825558357e-05, | |
| "loss": 0.2724, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.0012873960905401532, | |
| "grad_norm": 0.7678841352462769, | |
| "learning_rate": 6.28802751081779e-05, | |
| "loss": 0.2843, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.001307511654454843, | |
| "grad_norm": 0.6977100968360901, | |
| "learning_rate": 5.983045753470308e-05, | |
| "loss": 0.188, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.001327627218369533, | |
| "grad_norm": 0.7905102372169495, | |
| "learning_rate": 5.6824564766150726e-05, | |
| "loss": 0.4339, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.001347742782284223, | |
| "grad_norm": 0.5195531249046326, | |
| "learning_rate": 5.386588370213124e-05, | |
| "loss": 0.1489, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.0013678583461989129, | |
| "grad_norm": 2.699000597000122, | |
| "learning_rate": 5.095764961694922e-05, | |
| "loss": 0.6969, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.0013879739101136026, | |
| "grad_norm": 0.8617449402809143, | |
| "learning_rate": 4.810304262187852e-05, | |
| "loss": 0.3883, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.0014080894740282925, | |
| "grad_norm": 0.8697649240493774, | |
| "learning_rate": 4.530518418775733e-05, | |
| "loss": 0.2275, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0014282050379429824, | |
| "grad_norm": 0.7477262020111084, | |
| "learning_rate": 4.256713373170564e-05, | |
| "loss": 0.3324, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.0014483206018576723, | |
| "grad_norm": 0.6884785294532776, | |
| "learning_rate": 3.9891885271697496e-05, | |
| "loss": 0.1723, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.0014684361657723622, | |
| "grad_norm": 0.5269164443016052, | |
| "learning_rate": 3.7282364152646297e-05, | |
| "loss": 0.1525, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.0014885517296870522, | |
| "grad_norm": 1.167458415031433, | |
| "learning_rate": 3.4741423847583134e-05, | |
| "loss": 0.479, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.001508667293601742, | |
| "grad_norm": 0.5435552597045898, | |
| "learning_rate": 3.227184283742591e-05, | |
| "loss": 0.2228, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.001508667293601742, | |
| "eval_loss": 0.34874510765075684, | |
| "eval_runtime": 7329.6366, | |
| "eval_samples_per_second": 2.856, | |
| "eval_steps_per_second": 1.428, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.001528782857516432, | |
| "grad_norm": 0.7186751365661621, | |
| "learning_rate": 2.9876321572751144e-05, | |
| "loss": 0.1929, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.0015488984214311217, | |
| "grad_norm": 0.8120232224464417, | |
| "learning_rate": 2.7557479520891104e-05, | |
| "loss": 0.1906, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.0015690139853458116, | |
| "grad_norm": 0.5622069835662842, | |
| "learning_rate": 2.5317852301584643e-05, | |
| "loss": 0.158, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.0015891295492605016, | |
| "grad_norm": 0.6373627185821533, | |
| "learning_rate": 2.315988891431412e-05, | |
| "loss": 0.158, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.0016092451131751915, | |
| "grad_norm": 0.3394858241081238, | |
| "learning_rate": 2.1085949060360654e-05, | |
| "loss": 0.0549, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.0016293606770898814, | |
| "grad_norm": 0.9142265915870667, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.1498, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.0016494762410045713, | |
| "grad_norm": 0.5488215088844299, | |
| "learning_rate": 1.7199116885197995e-05, | |
| "loss": 0.086, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.0016695918049192612, | |
| "grad_norm": 0.6231745481491089, | |
| "learning_rate": 1.5390474757906446e-05, | |
| "loss": 0.1239, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.0016897073688339512, | |
| "grad_norm": 0.7093625664710999, | |
| "learning_rate": 1.3674351904242611e-05, | |
| "loss": 0.1512, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.0017098229327486409, | |
| "grad_norm": 1.516791820526123, | |
| "learning_rate": 1.2052624879351104e-05, | |
| "loss": 0.3605, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.0017299384966633308, | |
| "grad_norm": 0.8480135202407837, | |
| "learning_rate": 1.0527067017923654e-05, | |
| "loss": 0.2031, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.0017500540605780207, | |
| "grad_norm": 0.6130940318107605, | |
| "learning_rate": 9.09934649508375e-06, | |
| "loss": 0.1745, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.0017701696244927106, | |
| "grad_norm": 1.8014602661132812, | |
| "learning_rate": 7.771024502261526e-06, | |
| "loss": 0.4315, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.0017902851884074005, | |
| "grad_norm": 0.6862621307373047, | |
| "learning_rate": 6.543553540053926e-06, | |
| "loss": 0.1008, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.0018104007523220905, | |
| "grad_norm": 0.6760240197181702, | |
| "learning_rate": 5.418275829936537e-06, | |
| "loss": 0.1387, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0018305163162367804, | |
| "grad_norm": 2.04972767829895, | |
| "learning_rate": 4.3964218465642355e-06, | |
| "loss": 0.4774, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.0018506318801514703, | |
| "grad_norm": 3.159485101699829, | |
| "learning_rate": 3.4791089722651436e-06, | |
| "loss": 0.4218, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.00187074744406616, | |
| "grad_norm": 2.143138885498047, | |
| "learning_rate": 2.667340275199426e-06, | |
| "loss": 0.556, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.00189086300798085, | |
| "grad_norm": 1.6069244146347046, | |
| "learning_rate": 1.9620034125190644e-06, | |
| "loss": 0.4657, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.0019109785718955398, | |
| "grad_norm": 1.5652406215667725, | |
| "learning_rate": 1.3638696597277679e-06, | |
| "loss": 0.4702, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.0019310941358102298, | |
| "grad_norm": 2.650838613510132, | |
| "learning_rate": 8.735930673024806e-07, | |
| "loss": 0.6213, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.0019512096997249197, | |
| "grad_norm": 0.9253861904144287, | |
| "learning_rate": 4.917097454988584e-07, | |
| "loss": 0.2009, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.0019713252636396096, | |
| "grad_norm": 2.9420182704925537, | |
| "learning_rate": 2.1863727812254653e-07, | |
| "loss": 0.6738, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.0019914408275542995, | |
| "grad_norm": 3.0107245445251465, | |
| "learning_rate": 5.467426590739511e-08, | |
| "loss": 0.8191, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.0020115563914689895, | |
| "grad_norm": 1.9796432256698608, | |
| "learning_rate": 0.0, | |
| "loss": 0.4038, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0020115563914689895, | |
| "eval_loss": 0.34765490889549255, | |
| "eval_runtime": 7329.2018, | |
| "eval_samples_per_second": 2.856, | |
| "eval_steps_per_second": 1.428, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "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": 1.4874840035386982e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |