| { | |
| "best_metric": 0.8914665579795837, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-110", | |
| "epoch": 0.26252983293556087, | |
| "eval_steps": 5, | |
| "global_step": 110, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002386634844868735, | |
| "grad_norm": 1.6264880895614624, | |
| "learning_rate": 2e-05, | |
| "loss": 1.7576, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002386634844868735, | |
| "eval_loss": 1.4666008949279785, | |
| "eval_runtime": 26.2232, | |
| "eval_samples_per_second": 6.75, | |
| "eval_steps_per_second": 3.394, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00477326968973747, | |
| "grad_norm": 0.8592613935470581, | |
| "learning_rate": 4e-05, | |
| "loss": 0.8915, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007159904534606206, | |
| "grad_norm": 0.985676646232605, | |
| "learning_rate": 6e-05, | |
| "loss": 1.1643, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00954653937947494, | |
| "grad_norm": 1.3740118741989136, | |
| "learning_rate": 8e-05, | |
| "loss": 1.5305, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011933174224343675, | |
| "grad_norm": 0.9007270336151123, | |
| "learning_rate": 0.0001, | |
| "loss": 1.191, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.011933174224343675, | |
| "eval_loss": 1.421371340751648, | |
| "eval_runtime": 26.2293, | |
| "eval_samples_per_second": 6.748, | |
| "eval_steps_per_second": 3.393, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.014319809069212411, | |
| "grad_norm": 2.1037585735321045, | |
| "learning_rate": 0.00012, | |
| "loss": 1.6708, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.016706443914081145, | |
| "grad_norm": 0.9997168183326721, | |
| "learning_rate": 0.00014, | |
| "loss": 1.2175, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01909307875894988, | |
| "grad_norm": 1.029247522354126, | |
| "learning_rate": 0.00016, | |
| "loss": 1.2724, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.021479713603818614, | |
| "grad_norm": 1.2429360151290894, | |
| "learning_rate": 0.00018, | |
| "loss": 1.3846, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02386634844868735, | |
| "grad_norm": 0.4330953061580658, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4449, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02386634844868735, | |
| "eval_loss": 1.1578279733657837, | |
| "eval_runtime": 27.585, | |
| "eval_samples_per_second": 6.417, | |
| "eval_steps_per_second": 3.226, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.026252983293556086, | |
| "grad_norm": 0.9032881259918213, | |
| "learning_rate": 0.0001999979446958366, | |
| "loss": 1.1913, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.028639618138424822, | |
| "grad_norm": 1.043502926826477, | |
| "learning_rate": 0.00019999177886783194, | |
| "loss": 1.067, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.031026252983293555, | |
| "grad_norm": 0.984898030757904, | |
| "learning_rate": 0.00019998150276943902, | |
| "loss": 1.2715, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03341288782816229, | |
| "grad_norm": 0.8400496244430542, | |
| "learning_rate": 0.000199967116823068, | |
| "loss": 0.8158, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03579952267303103, | |
| "grad_norm": 0.925491452217102, | |
| "learning_rate": 0.0001999486216200688, | |
| "loss": 1.6707, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03579952267303103, | |
| "eval_loss": 1.0528874397277832, | |
| "eval_runtime": 26.2645, | |
| "eval_samples_per_second": 6.739, | |
| "eval_steps_per_second": 3.389, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03818615751789976, | |
| "grad_norm": 0.749546468257904, | |
| "learning_rate": 0.00019992601792070679, | |
| "loss": 0.9433, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0405727923627685, | |
| "grad_norm": 0.9893090128898621, | |
| "learning_rate": 0.00019989930665413147, | |
| "loss": 1.0754, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04295942720763723, | |
| "grad_norm": 0.8510335087776184, | |
| "learning_rate": 0.00019986848891833845, | |
| "loss": 1.2892, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.045346062052505964, | |
| "grad_norm": 0.8910903334617615, | |
| "learning_rate": 0.0001998335659801241, | |
| "loss": 0.8846, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0477326968973747, | |
| "grad_norm": 0.8577730059623718, | |
| "learning_rate": 0.00019979453927503364, | |
| "loss": 0.9342, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0477326968973747, | |
| "eval_loss": 1.0087474584579468, | |
| "eval_runtime": 26.2663, | |
| "eval_samples_per_second": 6.739, | |
| "eval_steps_per_second": 3.388, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.050119331742243436, | |
| "grad_norm": 0.9688092470169067, | |
| "learning_rate": 0.00019975141040730207, | |
| "loss": 1.1933, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05250596658711217, | |
| "grad_norm": 0.7774447202682495, | |
| "learning_rate": 0.0001997041811497882, | |
| "loss": 0.8412, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.05489260143198091, | |
| "grad_norm": 0.7570910453796387, | |
| "learning_rate": 0.00019965285344390184, | |
| "loss": 0.8872, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.057279236276849645, | |
| "grad_norm": 0.5232482552528381, | |
| "learning_rate": 0.00019959742939952392, | |
| "loss": 0.9852, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.059665871121718374, | |
| "grad_norm": 1.0864367485046387, | |
| "learning_rate": 0.00019953791129491983, | |
| "loss": 1.1447, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.059665871121718374, | |
| "eval_loss": 0.9940932393074036, | |
| "eval_runtime": 26.2586, | |
| "eval_samples_per_second": 6.741, | |
| "eval_steps_per_second": 3.389, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06205250596658711, | |
| "grad_norm": 0.9833227396011353, | |
| "learning_rate": 0.00019947430157664576, | |
| "loss": 1.4313, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.06443914081145585, | |
| "grad_norm": 0.7902147769927979, | |
| "learning_rate": 0.00019940660285944803, | |
| "loss": 1.0728, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06682577565632458, | |
| "grad_norm": 0.6701146364212036, | |
| "learning_rate": 0.00019933481792615583, | |
| "loss": 0.8888, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.06921241050119331, | |
| "grad_norm": 0.845893383026123, | |
| "learning_rate": 0.0001992589497275665, | |
| "loss": 0.9849, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.07159904534606205, | |
| "grad_norm": 0.7827535271644592, | |
| "learning_rate": 0.0001991790013823246, | |
| "loss": 1.331, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07159904534606205, | |
| "eval_loss": 0.9710781574249268, | |
| "eval_runtime": 26.2207, | |
| "eval_samples_per_second": 6.75, | |
| "eval_steps_per_second": 3.394, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07398568019093078, | |
| "grad_norm": 0.9344210028648376, | |
| "learning_rate": 0.00019909497617679348, | |
| "loss": 1.013, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.07637231503579953, | |
| "grad_norm": 0.6921480894088745, | |
| "learning_rate": 0.0001990068775649202, | |
| "loss": 0.6896, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.07875894988066826, | |
| "grad_norm": 0.804854154586792, | |
| "learning_rate": 0.00019891470916809362, | |
| "loss": 0.8884, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.081145584725537, | |
| "grad_norm": 0.7858572602272034, | |
| "learning_rate": 0.00019881847477499557, | |
| "loss": 0.8469, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.08353221957040573, | |
| "grad_norm": 0.7166551947593689, | |
| "learning_rate": 0.00019871817834144504, | |
| "loss": 0.9763, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08353221957040573, | |
| "eval_loss": 0.9543755054473877, | |
| "eval_runtime": 26.2507, | |
| "eval_samples_per_second": 6.743, | |
| "eval_steps_per_second": 3.39, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08591885441527446, | |
| "grad_norm": 0.7922567129135132, | |
| "learning_rate": 0.0001986138239902355, | |
| "loss": 1.0582, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0883054892601432, | |
| "grad_norm": 1.0015374422073364, | |
| "learning_rate": 0.0001985054160109657, | |
| "loss": 1.0839, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.09069212410501193, | |
| "grad_norm": 1.455461025238037, | |
| "learning_rate": 0.00019839295885986296, | |
| "loss": 1.2132, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.09307875894988067, | |
| "grad_norm": 0.781535267829895, | |
| "learning_rate": 0.0001982764571596004, | |
| "loss": 0.7504, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0954653937947494, | |
| "grad_norm": 0.8738696575164795, | |
| "learning_rate": 0.00019815591569910654, | |
| "loss": 0.6841, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0954653937947494, | |
| "eval_loss": 0.9494202136993408, | |
| "eval_runtime": 26.2561, | |
| "eval_samples_per_second": 6.741, | |
| "eval_steps_per_second": 3.39, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09785202863961814, | |
| "grad_norm": 1.0066485404968262, | |
| "learning_rate": 0.00019803133943336874, | |
| "loss": 1.1701, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.10023866348448687, | |
| "grad_norm": 0.8418964147567749, | |
| "learning_rate": 0.0001979027334832293, | |
| "loss": 1.0454, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1026252983293556, | |
| "grad_norm": 0.9529140591621399, | |
| "learning_rate": 0.00019777010313517518, | |
| "loss": 0.9311, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.10501193317422435, | |
| "grad_norm": 0.9450991749763489, | |
| "learning_rate": 0.00019763345384112043, | |
| "loss": 0.9843, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.10739856801909307, | |
| "grad_norm": 0.8391886353492737, | |
| "learning_rate": 0.00019749279121818235, | |
| "loss": 0.7273, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.10739856801909307, | |
| "eval_loss": 0.9417486786842346, | |
| "eval_runtime": 26.2253, | |
| "eval_samples_per_second": 6.749, | |
| "eval_steps_per_second": 3.394, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.10978520286396182, | |
| "grad_norm": 0.8711974620819092, | |
| "learning_rate": 0.00019734812104845047, | |
| "loss": 1.0276, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.11217183770883055, | |
| "grad_norm": 0.6002468466758728, | |
| "learning_rate": 0.00019719944927874881, | |
| "loss": 0.7602, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.11455847255369929, | |
| "grad_norm": 1.059345006942749, | |
| "learning_rate": 0.0001970467820203915, | |
| "loss": 1.3701, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.11694510739856802, | |
| "grad_norm": 0.9398312568664551, | |
| "learning_rate": 0.00019689012554893154, | |
| "loss": 0.9587, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.11933174224343675, | |
| "grad_norm": 0.8663720488548279, | |
| "learning_rate": 0.00019672948630390294, | |
| "loss": 0.766, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11933174224343675, | |
| "eval_loss": 0.9387193918228149, | |
| "eval_runtime": 26.2728, | |
| "eval_samples_per_second": 6.737, | |
| "eval_steps_per_second": 3.388, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12171837708830549, | |
| "grad_norm": 0.7873828411102295, | |
| "learning_rate": 0.00019656487088855592, | |
| "loss": 1.2591, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.12410501193317422, | |
| "grad_norm": 0.6708641648292542, | |
| "learning_rate": 0.00019639628606958533, | |
| "loss": 0.7497, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.12649164677804295, | |
| "grad_norm": 0.5296116471290588, | |
| "learning_rate": 0.0001962237387768529, | |
| "loss": 0.9209, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.1288782816229117, | |
| "grad_norm": 0.701153576374054, | |
| "learning_rate": 0.00019604723610310194, | |
| "loss": 0.9039, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.13126491646778043, | |
| "grad_norm": 0.607571005821228, | |
| "learning_rate": 0.00019586678530366606, | |
| "loss": 0.9841, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.13126491646778043, | |
| "eval_loss": 0.9331147074699402, | |
| "eval_runtime": 26.2365, | |
| "eval_samples_per_second": 6.746, | |
| "eval_steps_per_second": 3.392, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.13365155131264916, | |
| "grad_norm": 0.7479352951049805, | |
| "learning_rate": 0.00019568239379617088, | |
| "loss": 0.8665, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.1360381861575179, | |
| "grad_norm": 0.8115050196647644, | |
| "learning_rate": 0.00019549406916022905, | |
| "loss": 1.0235, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.13842482100238662, | |
| "grad_norm": 0.5173358917236328, | |
| "learning_rate": 0.00019530181913712872, | |
| "loss": 0.8548, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.14081145584725538, | |
| "grad_norm": 0.917434811592102, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 0.9314, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.1431980906921241, | |
| "grad_norm": 0.7886952757835388, | |
| "learning_rate": 0.00019490557470106686, | |
| "loss": 0.8733, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.1431980906921241, | |
| "eval_loss": 0.9312522411346436, | |
| "eval_runtime": 26.2683, | |
| "eval_samples_per_second": 6.738, | |
| "eval_steps_per_second": 3.388, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.14558472553699284, | |
| "grad_norm": 0.7969014644622803, | |
| "learning_rate": 0.00019470159657616215, | |
| "loss": 0.6603, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.14797136038186157, | |
| "grad_norm": 0.9583745002746582, | |
| "learning_rate": 0.00019449372563954293, | |
| "loss": 1.466, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.15035799522673032, | |
| "grad_norm": 0.7162270545959473, | |
| "learning_rate": 0.0001942819704359693, | |
| "loss": 0.8824, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.15274463007159905, | |
| "grad_norm": 0.47627589106559753, | |
| "learning_rate": 0.00019406633966986828, | |
| "loss": 0.6296, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.15513126491646778, | |
| "grad_norm": 0.7122361063957214, | |
| "learning_rate": 0.00019384684220497605, | |
| "loss": 0.64, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.15513126491646778, | |
| "eval_loss": 0.9237020015716553, | |
| "eval_runtime": 26.2941, | |
| "eval_samples_per_second": 6.732, | |
| "eval_steps_per_second": 3.385, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.1575178997613365, | |
| "grad_norm": 0.8619460463523865, | |
| "learning_rate": 0.00019362348706397373, | |
| "loss": 1.1417, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.15990453460620524, | |
| "grad_norm": 0.7796176075935364, | |
| "learning_rate": 0.00019339628342811632, | |
| "loss": 0.859, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.162291169451074, | |
| "grad_norm": 0.8874034285545349, | |
| "learning_rate": 0.0001931652406368554, | |
| "loss": 0.9786, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.16467780429594273, | |
| "grad_norm": 0.7292467951774597, | |
| "learning_rate": 0.0001929303681874552, | |
| "loss": 0.8093, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.16706443914081145, | |
| "grad_norm": 0.8368440270423889, | |
| "learning_rate": 0.0001926916757346022, | |
| "loss": 1.3638, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.16706443914081145, | |
| "eval_loss": 0.9212387800216675, | |
| "eval_runtime": 26.2497, | |
| "eval_samples_per_second": 6.743, | |
| "eval_steps_per_second": 3.391, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.16945107398568018, | |
| "grad_norm": 0.6919611692428589, | |
| "learning_rate": 0.00019244917309000817, | |
| "loss": 0.9292, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.1718377088305489, | |
| "grad_norm": 0.8706820607185364, | |
| "learning_rate": 0.00019220287022200707, | |
| "loss": 1.122, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.17422434367541767, | |
| "grad_norm": 0.6912488341331482, | |
| "learning_rate": 0.0001919527772551451, | |
| "loss": 1.0077, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.1766109785202864, | |
| "grad_norm": 0.6089036464691162, | |
| "learning_rate": 0.00019169890446976454, | |
| "loss": 0.9816, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.17899761336515513, | |
| "grad_norm": 0.7333152294158936, | |
| "learning_rate": 0.00019144126230158127, | |
| "loss": 0.8958, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.17899761336515513, | |
| "eval_loss": 0.9194671511650085, | |
| "eval_runtime": 26.2263, | |
| "eval_samples_per_second": 6.749, | |
| "eval_steps_per_second": 3.394, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.18138424821002386, | |
| "grad_norm": 0.7732102870941162, | |
| "learning_rate": 0.0001911798613412557, | |
| "loss": 0.8417, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.18377088305489261, | |
| "grad_norm": 0.6444439888000488, | |
| "learning_rate": 0.0001909147123339575, | |
| "loss": 0.9722, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.18615751789976134, | |
| "grad_norm": 0.522572934627533, | |
| "learning_rate": 0.0001906458261789238, | |
| "loss": 0.7848, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.18854415274463007, | |
| "grad_norm": 0.6048774719238281, | |
| "learning_rate": 0.00019037321392901136, | |
| "loss": 1.0934, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.1909307875894988, | |
| "grad_norm": 0.7766179442405701, | |
| "learning_rate": 0.0001900968867902419, | |
| "loss": 0.8923, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.1909307875894988, | |
| "eval_loss": 0.9133721590042114, | |
| "eval_runtime": 26.2379, | |
| "eval_samples_per_second": 6.746, | |
| "eval_steps_per_second": 3.392, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.19331742243436753, | |
| "grad_norm": 0.6204676032066345, | |
| "learning_rate": 0.0001898168561213419, | |
| "loss": 0.7503, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.1957040572792363, | |
| "grad_norm": 0.5830619931221008, | |
| "learning_rate": 0.0001895331334332753, | |
| "loss": 0.7373, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.19809069212410502, | |
| "grad_norm": 0.6380212306976318, | |
| "learning_rate": 0.0001892457303887706, | |
| "loss": 0.789, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.20047732696897375, | |
| "grad_norm": 0.6974972486495972, | |
| "learning_rate": 0.0001889546588018412, | |
| "loss": 0.8987, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.20286396181384247, | |
| "grad_norm": 0.6037717461585999, | |
| "learning_rate": 0.00018865993063730004, | |
| "loss": 1.1555, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.20286396181384247, | |
| "eval_loss": 0.9121592044830322, | |
| "eval_runtime": 26.2683, | |
| "eval_samples_per_second": 6.738, | |
| "eval_steps_per_second": 3.388, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.2052505966587112, | |
| "grad_norm": 0.5582723617553711, | |
| "learning_rate": 0.00018836155801026753, | |
| "loss": 0.6236, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.20763723150357996, | |
| "grad_norm": 0.7444891929626465, | |
| "learning_rate": 0.0001880595531856738, | |
| "loss": 0.6428, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.2100238663484487, | |
| "grad_norm": 0.5842642188072205, | |
| "learning_rate": 0.00018775392857775432, | |
| "loss": 0.9149, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.21241050119331742, | |
| "grad_norm": 0.6907650232315063, | |
| "learning_rate": 0.00018744469674953956, | |
| "loss": 0.8653, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.21479713603818615, | |
| "grad_norm": 0.7942304611206055, | |
| "learning_rate": 0.00018713187041233896, | |
| "loss": 0.7069, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.21479713603818615, | |
| "eval_loss": 0.910210132598877, | |
| "eval_runtime": 26.2879, | |
| "eval_samples_per_second": 6.733, | |
| "eval_steps_per_second": 3.386, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.2171837708830549, | |
| "grad_norm": 0.7289912104606628, | |
| "learning_rate": 0.00018681546242521786, | |
| "loss": 0.7671, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.21957040572792363, | |
| "grad_norm": 0.6675541400909424, | |
| "learning_rate": 0.00018649548579446936, | |
| "loss": 0.6645, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.22195704057279236, | |
| "grad_norm": 0.4568694829940796, | |
| "learning_rate": 0.0001861719536730795, | |
| "loss": 0.7777, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.2243436754176611, | |
| "grad_norm": 0.715552568435669, | |
| "learning_rate": 0.00018584487936018661, | |
| "loss": 1.1339, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.22673031026252982, | |
| "grad_norm": 0.8277347087860107, | |
| "learning_rate": 0.00018551427630053463, | |
| "loss": 0.9398, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.22673031026252982, | |
| "eval_loss": 0.9004982113838196, | |
| "eval_runtime": 26.2476, | |
| "eval_samples_per_second": 6.743, | |
| "eval_steps_per_second": 3.391, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.22911694510739858, | |
| "grad_norm": 0.7335620522499084, | |
| "learning_rate": 0.00018518015808392045, | |
| "loss": 0.8793, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.2315035799522673, | |
| "grad_norm": 0.5709030032157898, | |
| "learning_rate": 0.00018484253844463526, | |
| "loss": 0.7161, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.23389021479713604, | |
| "grad_norm": 0.6625402569770813, | |
| "learning_rate": 0.00018450143126090015, | |
| "loss": 0.8631, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.23627684964200477, | |
| "grad_norm": 0.3961223065853119, | |
| "learning_rate": 0.00018415685055429533, | |
| "loss": 0.6657, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.2386634844868735, | |
| "grad_norm": 0.8134841322898865, | |
| "learning_rate": 0.00018380881048918405, | |
| "loss": 1.1527, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2386634844868735, | |
| "eval_loss": 0.8966440558433533, | |
| "eval_runtime": 26.2452, | |
| "eval_samples_per_second": 6.744, | |
| "eval_steps_per_second": 3.391, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.24105011933174225, | |
| "grad_norm": 0.6637277007102966, | |
| "learning_rate": 0.00018345732537213027, | |
| "loss": 1.175, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.24343675417661098, | |
| "grad_norm": 0.5118420124053955, | |
| "learning_rate": 0.00018310240965131041, | |
| "loss": 0.852, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.2458233890214797, | |
| "grad_norm": 0.6100435256958008, | |
| "learning_rate": 0.00018274407791591966, | |
| "loss": 0.8036, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.24821002386634844, | |
| "grad_norm": 0.8629751801490784, | |
| "learning_rate": 0.00018238234489557215, | |
| "loss": 0.9638, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.25059665871121717, | |
| "grad_norm": 0.6925487518310547, | |
| "learning_rate": 0.0001820172254596956, | |
| "loss": 1.0022, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.25059665871121717, | |
| "eval_loss": 0.8950950503349304, | |
| "eval_runtime": 26.2737, | |
| "eval_samples_per_second": 6.737, | |
| "eval_steps_per_second": 3.387, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.2529832935560859, | |
| "grad_norm": 0.6932248473167419, | |
| "learning_rate": 0.00018164873461691986, | |
| "loss": 0.7119, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.2553699284009546, | |
| "grad_norm": 0.6727349162101746, | |
| "learning_rate": 0.00018127688751446027, | |
| "loss": 1.0059, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.2577565632458234, | |
| "grad_norm": 0.7314417362213135, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.8165, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.26014319809069214, | |
| "grad_norm": 0.5489733219146729, | |
| "learning_rate": 0.0001805231858085356, | |
| "loss": 0.8262, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.26252983293556087, | |
| "grad_norm": 0.5698820948600769, | |
| "learning_rate": 0.00018014136218679567, | |
| "loss": 0.7001, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.26252983293556087, | |
| "eval_loss": 0.8914665579795837, | |
| "eval_runtime": 26.2981, | |
| "eval_samples_per_second": 6.731, | |
| "eval_steps_per_second": 3.384, | |
| "step": 110 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.153367887413248e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |