| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0785876993166287, | |
| "eval_steps": 500, | |
| "global_step": 138, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005694760820045558, | |
| "grad_norm": 0.9193857312202454, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 0.9288, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011389521640091116, | |
| "grad_norm": 0.8991456031799316, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 0.9457, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0017084282460136675, | |
| "grad_norm": 1.1229982376098633, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 0.9705, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002277904328018223, | |
| "grad_norm": 1.1453852653503418, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 0.8237, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0028473804100227792, | |
| "grad_norm": 0.6836767196655273, | |
| "learning_rate": 0.00015, | |
| "loss": 0.6138, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003416856492027335, | |
| "grad_norm": 0.7178201079368591, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 0.715, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003986332574031891, | |
| "grad_norm": 0.6292722225189209, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 0.8324, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004555808656036446, | |
| "grad_norm": 1.0551400184631348, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 0.7891, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005125284738041002, | |
| "grad_norm": 2.0253489017486572, | |
| "learning_rate": 0.00027, | |
| "loss": 1.188, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0056947608200455585, | |
| "grad_norm": 1.0278229713439941, | |
| "learning_rate": 0.0003, | |
| "loss": 0.7582, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006264236902050114, | |
| "grad_norm": 1.3169053792953491, | |
| "learning_rate": 0.0002999548228044306, | |
| "loss": 0.7924, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00683371298405467, | |
| "grad_norm": 0.8358129262924194, | |
| "learning_rate": 0.00029981931843077583, | |
| "loss": 0.7108, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.007403189066059226, | |
| "grad_norm": 1.0881885290145874, | |
| "learning_rate": 0.0002995935685018035, | |
| "loss": 0.7324, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.007972665148063782, | |
| "grad_norm": 1.1146137714385986, | |
| "learning_rate": 0.00029927770900082954, | |
| "loss": 1.2375, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.008542141230068337, | |
| "grad_norm": 0.5502291917800903, | |
| "learning_rate": 0.0002988719301898065, | |
| "loss": 0.6301, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009111617312072893, | |
| "grad_norm": 0.684746503829956, | |
| "learning_rate": 0.00029837647649471715, | |
| "loss": 0.6484, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00968109339407745, | |
| "grad_norm": 0.6915183663368225, | |
| "learning_rate": 0.00029779164635834114, | |
| "loss": 1.5319, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.010250569476082005, | |
| "grad_norm": 0.6584042906761169, | |
| "learning_rate": 0.00029711779206048454, | |
| "loss": 0.7015, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01082004555808656, | |
| "grad_norm": 0.6344502568244934, | |
| "learning_rate": 0.00029635531950577925, | |
| "loss": 0.6405, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.011389521640091117, | |
| "grad_norm": 0.8625004291534424, | |
| "learning_rate": 0.0002955046879791816, | |
| "loss": 0.6721, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.011958997722095672, | |
| "grad_norm": 0.8597177863121033, | |
| "learning_rate": 0.00029456640986931596, | |
| "loss": 0.6415, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.012528473804100227, | |
| "grad_norm": 1.4716626405715942, | |
| "learning_rate": 0.0002935410503598313, | |
| "loss": 0.952, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.013097949886104784, | |
| "grad_norm": 0.5828580260276794, | |
| "learning_rate": 0.00029242922708895547, | |
| "loss": 0.5977, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.01366742596810934, | |
| "grad_norm": 0.6336590647697449, | |
| "learning_rate": 0.00029123160977745306, | |
| "loss": 0.8268, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.014236902050113895, | |
| "grad_norm": 0.6400074362754822, | |
| "learning_rate": 0.0002899489198252108, | |
| "loss": 0.7116, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.014806378132118452, | |
| "grad_norm": 0.914237380027771, | |
| "learning_rate": 0.000288581929876693, | |
| "loss": 0.6563, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.015375854214123007, | |
| "grad_norm": 0.7890664339065552, | |
| "learning_rate": 0.0002871314633555296, | |
| "loss": 0.9234, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.015945330296127564, | |
| "grad_norm": 0.9337290525436401, | |
| "learning_rate": 0.0002855983939685165, | |
| "loss": 0.7655, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.01651480637813212, | |
| "grad_norm": 0.9062933325767517, | |
| "learning_rate": 0.00028398364517932725, | |
| "loss": 0.6479, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.017084282460136675, | |
| "grad_norm": 0.5920599102973938, | |
| "learning_rate": 0.0002822881896522532, | |
| "loss": 0.6417, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01765375854214123, | |
| "grad_norm": 0.7619308829307556, | |
| "learning_rate": 0.0002805130486663067, | |
| "loss": 0.7647, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.018223234624145785, | |
| "grad_norm": 0.8592938184738159, | |
| "learning_rate": 0.0002786592915000408, | |
| "loss": 1.0644, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.01879271070615034, | |
| "grad_norm": 0.584583044052124, | |
| "learning_rate": 0.000276728034787456, | |
| "loss": 0.5707, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0193621867881549, | |
| "grad_norm": 0.6947116851806641, | |
| "learning_rate": 0.0002747204418453818, | |
| "loss": 0.8087, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.019931662870159454, | |
| "grad_norm": 0.5154379606246948, | |
| "learning_rate": 0.0002726377219727375, | |
| "loss": 0.6937, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.02050113895216401, | |
| "grad_norm": 0.6641525626182556, | |
| "learning_rate": 0.0002704811297220967, | |
| "loss": 0.7324, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.021070615034168565, | |
| "grad_norm": 0.776289701461792, | |
| "learning_rate": 0.00026825196414399094, | |
| "loss": 0.6164, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.02164009111617312, | |
| "grad_norm": 0.9698323607444763, | |
| "learning_rate": 0.0002659515680044105, | |
| "loss": 0.5876, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.022209567198177675, | |
| "grad_norm": 0.9234256744384766, | |
| "learning_rate": 0.00026358132697597265, | |
| "loss": 1.6872, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.022779043280182234, | |
| "grad_norm": 0.8341031670570374, | |
| "learning_rate": 0.00026114266880324387, | |
| "loss": 0.7148, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02334851936218679, | |
| "grad_norm": 0.7260201573371887, | |
| "learning_rate": 0.00025863706244272003, | |
| "loss": 0.6195, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.023917995444191344, | |
| "grad_norm": 0.5485382080078125, | |
| "learning_rate": 0.00025606601717798207, | |
| "loss": 0.6015, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0244874715261959, | |
| "grad_norm": 0.83427494764328, | |
| "learning_rate": 0.00025343108171056, | |
| "loss": 0.7354, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.025056947608200455, | |
| "grad_norm": 0.7569791674613953, | |
| "learning_rate": 0.00025073384322705274, | |
| "loss": 0.7379, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.02562642369020501, | |
| "grad_norm": 0.7086009383201599, | |
| "learning_rate": 0.00024797592644306646, | |
| "loss": 0.8229, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02619589977220957, | |
| "grad_norm": 0.6626051068305969, | |
| "learning_rate": 0.0002451589926245468, | |
| "loss": 0.7937, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.026765375854214124, | |
| "grad_norm": 1.0067198276519775, | |
| "learning_rate": 0.000242284738587094, | |
| "loss": 0.94, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.02733485193621868, | |
| "grad_norm": 0.6433237791061401, | |
| "learning_rate": 0.000239354895673865, | |
| "loss": 0.9452, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.027904328018223234, | |
| "grad_norm": 0.6352181434631348, | |
| "learning_rate": 0.00023637122871267679, | |
| "loss": 0.6538, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.02847380410022779, | |
| "grad_norm": 0.7389889359474182, | |
| "learning_rate": 0.0002333355349529403, | |
| "loss": 0.989, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.029043280182232345, | |
| "grad_norm": 0.7596966028213501, | |
| "learning_rate": 0.00023024964298306458, | |
| "loss": 0.6397, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.029612756264236904, | |
| "grad_norm": 0.6516755223274231, | |
| "learning_rate": 0.00022711541162898321, | |
| "loss": 0.5003, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.03018223234624146, | |
| "grad_norm": 0.8451756238937378, | |
| "learning_rate": 0.0002239347288344676, | |
| "loss": 0.738, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.030751708428246014, | |
| "grad_norm": 0.7065162062644958, | |
| "learning_rate": 0.00022070951052389966, | |
| "loss": 0.7718, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.03132118451025057, | |
| "grad_norm": 0.9125147461891174, | |
| "learning_rate": 0.00021744169944819098, | |
| "loss": 0.5715, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.03189066059225513, | |
| "grad_norm": 0.5039160847663879, | |
| "learning_rate": 0.0002141332640145423, | |
| "loss": 0.5745, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.03246013667425968, | |
| "grad_norm": 0.5523383617401123, | |
| "learning_rate": 0.00021078619710074845, | |
| "loss": 0.9072, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.03302961275626424, | |
| "grad_norm": 0.7476831674575806, | |
| "learning_rate": 0.00020740251485476345, | |
| "loss": 0.4698, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.033599088838268794, | |
| "grad_norm": 0.6698426604270935, | |
| "learning_rate": 0.00020398425548024822, | |
| "loss": 0.6769, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.03416856492027335, | |
| "grad_norm": 0.7437167167663574, | |
| "learning_rate": 0.00020053347800883298, | |
| "loss": 0.6624, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.034738041002277904, | |
| "grad_norm": 0.5557659268379211, | |
| "learning_rate": 0.00019705226105983374, | |
| "loss": 0.7612, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.03530751708428246, | |
| "grad_norm": 0.5920267701148987, | |
| "learning_rate": 0.0001935427015881693, | |
| "loss": 0.6359, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.035876993166287015, | |
| "grad_norm": 0.5547272562980652, | |
| "learning_rate": 0.00019000691362123473, | |
| "loss": 0.5502, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.03644646924829157, | |
| "grad_norm": 0.6265895366668701, | |
| "learning_rate": 0.0001864470269854896, | |
| "loss": 0.8296, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.037015945330296125, | |
| "grad_norm": 0.5109124779701233, | |
| "learning_rate": 0.00018286518602353045, | |
| "loss": 0.6811, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.03758542141230068, | |
| "grad_norm": 0.733314573764801, | |
| "learning_rate": 0.00017926354830241924, | |
| "loss": 0.9034, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.038154897494305236, | |
| "grad_norm": 0.5381625294685364, | |
| "learning_rate": 0.00017564428331404519, | |
| "loss": 0.6674, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.0387243735763098, | |
| "grad_norm": 0.6308789849281311, | |
| "learning_rate": 0.00017200957116830423, | |
| "loss": 0.6398, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.03929384965831435, | |
| "grad_norm": 0.6676629185676575, | |
| "learning_rate": 0.00016836160127988242, | |
| "loss": 0.57, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.03986332574031891, | |
| "grad_norm": 0.72255539894104, | |
| "learning_rate": 0.0001647025710494341, | |
| "loss": 0.6134, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.040432801822323464, | |
| "grad_norm": 1.10958731174469, | |
| "learning_rate": 0.00016103468453995012, | |
| "loss": 0.9271, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.04100227790432802, | |
| "grad_norm": 0.5311421751976013, | |
| "learning_rate": 0.0001573601511491127, | |
| "loss": 0.6661, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.041571753986332574, | |
| "grad_norm": 0.8206638097763062, | |
| "learning_rate": 0.00015368118427843682, | |
| "loss": 0.8327, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.04214123006833713, | |
| "grad_norm": 0.5865733027458191, | |
| "learning_rate": 0.00015, | |
| "loss": 0.5316, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.042710706150341685, | |
| "grad_norm": 0.674359917640686, | |
| "learning_rate": 0.00014631881572156315, | |
| "loss": 1.232, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.04328018223234624, | |
| "grad_norm": 0.6954506039619446, | |
| "learning_rate": 0.0001426398488508873, | |
| "loss": 0.6289, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.043849658314350795, | |
| "grad_norm": 0.6149243116378784, | |
| "learning_rate": 0.00013896531546004988, | |
| "loss": 0.6659, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.04441913439635535, | |
| "grad_norm": 0.6586117148399353, | |
| "learning_rate": 0.0001352974289505659, | |
| "loss": 0.9493, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.044988610478359906, | |
| "grad_norm": 0.6128969192504883, | |
| "learning_rate": 0.00013163839872011758, | |
| "loss": 1.0356, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.04555808656036447, | |
| "grad_norm": 0.6175865530967712, | |
| "learning_rate": 0.00012799042883169574, | |
| "loss": 0.7532, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.04612756264236902, | |
| "grad_norm": 0.7808921933174133, | |
| "learning_rate": 0.0001243557166859548, | |
| "loss": 1.015, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.04669703872437358, | |
| "grad_norm": 1.351828932762146, | |
| "learning_rate": 0.00012073645169758076, | |
| "loss": 0.9374, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.04726651480637813, | |
| "grad_norm": 0.598646879196167, | |
| "learning_rate": 0.00011713481397646953, | |
| "loss": 0.5562, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.04783599088838269, | |
| "grad_norm": 0.7442788481712341, | |
| "learning_rate": 0.00011355297301451042, | |
| "loss": 0.75, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.048405466970387244, | |
| "grad_norm": 0.5332076549530029, | |
| "learning_rate": 0.00010999308637876524, | |
| "loss": 0.6766, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.0489749430523918, | |
| "grad_norm": 1.0476224422454834, | |
| "learning_rate": 0.00010645729841183066, | |
| "loss": 0.6271, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.049544419134396354, | |
| "grad_norm": 0.8156277537345886, | |
| "learning_rate": 0.00010294773894016627, | |
| "loss": 0.8984, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.05011389521640091, | |
| "grad_norm": 0.8451378345489502, | |
| "learning_rate": 9.946652199116699e-05, | |
| "loss": 1.0814, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.050683371298405465, | |
| "grad_norm": 0.6506671905517578, | |
| "learning_rate": 9.601574451975175e-05, | |
| "loss": 0.5343, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.05125284738041002, | |
| "grad_norm": 1.0723323822021484, | |
| "learning_rate": 9.259748514523653e-05, | |
| "loss": 1.1407, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.051822323462414575, | |
| "grad_norm": 0.6675905585289001, | |
| "learning_rate": 8.921380289925153e-05, | |
| "loss": 0.8981, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.05239179954441914, | |
| "grad_norm": 0.851328432559967, | |
| "learning_rate": 8.586673598545771e-05, | |
| "loss": 0.7855, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.05296127562642369, | |
| "grad_norm": 0.5953764915466309, | |
| "learning_rate": 8.255830055180899e-05, | |
| "loss": 0.6019, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.05353075170842825, | |
| "grad_norm": 0.6898136138916016, | |
| "learning_rate": 7.929048947610034e-05, | |
| "loss": 0.6316, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.0541002277904328, | |
| "grad_norm": 0.766689658164978, | |
| "learning_rate": 7.606527116553241e-05, | |
| "loss": 0.7684, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.05466970387243736, | |
| "grad_norm": 0.9130173325538635, | |
| "learning_rate": 7.288458837101675e-05, | |
| "loss": 1.0119, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.055239179954441914, | |
| "grad_norm": 0.7758641242980957, | |
| "learning_rate": 6.975035701693544e-05, | |
| "loss": 0.7098, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.05580865603644647, | |
| "grad_norm": 0.5639253258705139, | |
| "learning_rate": 6.66644650470597e-05, | |
| "loss": 0.5637, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.056378132118451024, | |
| "grad_norm": 0.9065825939178467, | |
| "learning_rate": 6.362877128732319e-05, | |
| "loss": 1.149, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.05694760820045558, | |
| "grad_norm": 0.75728839635849, | |
| "learning_rate": 6.064510432613499e-05, | |
| "loss": 0.4102, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.057517084282460135, | |
| "grad_norm": 0.7174970507621765, | |
| "learning_rate": 5.771526141290599e-05, | |
| "loss": 0.7149, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.05808656036446469, | |
| "grad_norm": 0.5997675657272339, | |
| "learning_rate": 5.4841007375453186e-05, | |
| "loss": 0.4369, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.058656036446469245, | |
| "grad_norm": 0.6755107641220093, | |
| "learning_rate": 5.2024073556933516e-05, | |
| "loss": 1.361, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.05922551252847381, | |
| "grad_norm": 0.8155584931373596, | |
| "learning_rate": 4.926615677294723e-05, | |
| "loss": 0.6092, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.05979498861047836, | |
| "grad_norm": 0.7561736702919006, | |
| "learning_rate": 4.656891828943996e-05, | |
| "loss": 0.8085, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.06036446469248292, | |
| "grad_norm": 0.6462244391441345, | |
| "learning_rate": 4.3933982822017876e-05, | |
| "loss": 0.661, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.06093394077448747, | |
| "grad_norm": 0.8051128387451172, | |
| "learning_rate": 4.136293755727998e-05, | |
| "loss": 0.7713, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.06150341685649203, | |
| "grad_norm": 1.8678494691848755, | |
| "learning_rate": 3.885733119675616e-05, | |
| "loss": 1.0606, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.062072892938496584, | |
| "grad_norm": 0.5828897953033447, | |
| "learning_rate": 3.641867302402731e-05, | |
| "loss": 0.5834, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.06264236902050115, | |
| "grad_norm": 0.4921259582042694, | |
| "learning_rate": 3.404843199558945e-05, | |
| "loss": 0.6211, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.0632118451025057, | |
| "grad_norm": 0.7523202896118164, | |
| "learning_rate": 3.174803585600906e-05, | |
| "loss": 0.5977, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.06378132118451026, | |
| "grad_norm": 0.618629515171051, | |
| "learning_rate": 2.9518870277903274e-05, | |
| "loss": 0.5802, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.06435079726651481, | |
| "grad_norm": 0.633359968662262, | |
| "learning_rate": 2.7362278027262457e-05, | |
| "loss": 0.8338, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.06492027334851937, | |
| "grad_norm": 0.5951647758483887, | |
| "learning_rate": 2.5279558154618197e-05, | |
| "loss": 0.5764, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.06548974943052392, | |
| "grad_norm": 0.5431082248687744, | |
| "learning_rate": 2.3271965212543932e-05, | |
| "loss": 0.6116, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.06605922551252848, | |
| "grad_norm": 0.6911126971244812, | |
| "learning_rate": 2.1340708499959197e-05, | |
| "loss": 0.8577, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.06662870159453303, | |
| "grad_norm": 0.7030333280563354, | |
| "learning_rate": 1.9486951333693296e-05, | |
| "loss": 0.7916, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.06719817767653759, | |
| "grad_norm": 0.6063715815544128, | |
| "learning_rate": 1.7711810347746757e-05, | |
| "loss": 0.6928, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.06776765375854214, | |
| "grad_norm": 0.6492345333099365, | |
| "learning_rate": 1.6016354820672715e-05, | |
| "loss": 0.6717, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.0683371298405467, | |
| "grad_norm": 0.658710777759552, | |
| "learning_rate": 1.4401606031483497e-05, | |
| "loss": 1.0441, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.06890660592255125, | |
| "grad_norm": 0.6208887696266174, | |
| "learning_rate": 1.2868536644470396e-05, | |
| "loss": 0.793, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.06947608200455581, | |
| "grad_norm": 0.520664393901825, | |
| "learning_rate": 1.1418070123306989e-05, | |
| "loss": 0.5236, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.07004555808656036, | |
| "grad_norm": 0.5397936701774597, | |
| "learning_rate": 1.0051080174789172e-05, | |
| "loss": 0.6599, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.07061503416856492, | |
| "grad_norm": 0.6907640695571899, | |
| "learning_rate": 8.768390222546895e-06, | |
| "loss": 0.7875, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.07118451025056947, | |
| "grad_norm": 0.573017418384552, | |
| "learning_rate": 7.570772911044498e-06, | |
| "loss": 0.5655, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.07175398633257403, | |
| "grad_norm": 1.2410931587219238, | |
| "learning_rate": 6.458949640168675e-06, | |
| "loss": 0.6824, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.07232346241457858, | |
| "grad_norm": 0.692986786365509, | |
| "learning_rate": 5.4335901306840235e-06, | |
| "loss": 0.6636, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.07289293849658314, | |
| "grad_norm": 0.5771859288215637, | |
| "learning_rate": 4.495312020818403e-06, | |
| "loss": 0.9473, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.0734624145785877, | |
| "grad_norm": 0.8466888666152954, | |
| "learning_rate": 3.6446804942207306e-06, | |
| "loss": 0.7754, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.07403189066059225, | |
| "grad_norm": 0.5004900097846985, | |
| "learning_rate": 2.882207939515435e-06, | |
| "loss": 0.7227, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.0746013667425968, | |
| "grad_norm": 0.8404062390327454, | |
| "learning_rate": 2.2083536416588165e-06, | |
| "loss": 0.5737, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.07517084282460136, | |
| "grad_norm": 0.46463948488235474, | |
| "learning_rate": 1.6235235052828476e-06, | |
| "loss": 0.6784, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.07574031890660592, | |
| "grad_norm": 0.7300965785980225, | |
| "learning_rate": 1.128069810193505e-06, | |
| "loss": 0.987, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.07630979498861047, | |
| "grad_norm": 0.9501856565475464, | |
| "learning_rate": 7.222909991704773e-07, | |
| "loss": 0.5392, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.07687927107061504, | |
| "grad_norm": 0.6093735694885254, | |
| "learning_rate": 4.064314981964689e-07, | |
| "loss": 0.801, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.0774487471526196, | |
| "grad_norm": 0.8983132839202881, | |
| "learning_rate": 1.8068156922413924e-07, | |
| "loss": 0.7463, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.07801822323462415, | |
| "grad_norm": 0.7183220982551575, | |
| "learning_rate": 4.51771955693625e-08, | |
| "loss": 0.6387, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.0785876993166287, | |
| "grad_norm": 0.6416277885437012, | |
| "learning_rate": 0.0, | |
| "loss": 1.1154, | |
| "step": 138 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 138, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "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": 2.7728037223071744e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |