| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 10.0, |
| "eval_steps": 50, |
| "global_step": 500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.02, |
| "grad_norm": 520.4644775390625, |
| "learning_rate": 1.0000000000000002e-06, |
| "loss": 5.0715, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.04, |
| "grad_norm": 520.4757080078125, |
| "learning_rate": 2.0000000000000003e-06, |
| "loss": 5.072, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.06, |
| "grad_norm": 518.3416748046875, |
| "learning_rate": 3e-06, |
| "loss": 5.0258, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.08, |
| "grad_norm": 494.84033203125, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 4.5896, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 413.3812561035156, |
| "learning_rate": 5e-06, |
| "loss": 3.8571, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.12, |
| "grad_norm": 145.95079040527344, |
| "learning_rate": 6e-06, |
| "loss": 2.352, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.14, |
| "grad_norm": 90.29026794433594, |
| "learning_rate": 7.000000000000001e-06, |
| "loss": 2.0816, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 15.726278305053711, |
| "learning_rate": 8.000000000000001e-06, |
| "loss": 1.712, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.18, |
| "grad_norm": 7.5671234130859375, |
| "learning_rate": 9e-06, |
| "loss": 1.6391, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 5.866340637207031, |
| "learning_rate": 1e-05, |
| "loss": 1.3099, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.22, |
| "grad_norm": 5.263887882232666, |
| "learning_rate": 1.1000000000000001e-05, |
| "loss": 1.1459, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.24, |
| "grad_norm": 5.094001770019531, |
| "learning_rate": 1.2e-05, |
| "loss": 0.9704, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.26, |
| "grad_norm": 6.369605541229248, |
| "learning_rate": 1.3000000000000001e-05, |
| "loss": 0.6508, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.28, |
| "grad_norm": 5.96874475479126, |
| "learning_rate": 1.4000000000000001e-05, |
| "loss": 0.3816, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.3, |
| "grad_norm": 5.774180889129639, |
| "learning_rate": 1.5e-05, |
| "loss": 0.2447, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.32, |
| "grad_norm": 2.370732545852661, |
| "learning_rate": 1.6000000000000003e-05, |
| "loss": 0.1072, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.34, |
| "grad_norm": 1.443320870399475, |
| "learning_rate": 1.7000000000000003e-05, |
| "loss": 0.0475, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.36, |
| "grad_norm": 1.2612560987472534, |
| "learning_rate": 1.8e-05, |
| "loss": 0.0294, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.38, |
| "grad_norm": 1.5056159496307373, |
| "learning_rate": 1.9e-05, |
| "loss": 0.0268, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 0.9794118404388428, |
| "learning_rate": 2e-05, |
| "loss": 0.0202, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.42, |
| "grad_norm": 0.7181198596954346, |
| "learning_rate": 2.1e-05, |
| "loss": 0.0179, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.44, |
| "grad_norm": 0.794865071773529, |
| "learning_rate": 2.2000000000000003e-05, |
| "loss": 0.0152, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.46, |
| "grad_norm": 1.4117693901062012, |
| "learning_rate": 2.3000000000000003e-05, |
| "loss": 0.0144, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.48, |
| "grad_norm": 3.0236976146698, |
| "learning_rate": 2.4e-05, |
| "loss": 0.0175, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 3.1012909412384033, |
| "learning_rate": 2.5e-05, |
| "loss": 0.0179, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.52, |
| "grad_norm": 8.274877548217773, |
| "learning_rate": 2.6000000000000002e-05, |
| "loss": 0.06, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.54, |
| "grad_norm": 4.594793319702148, |
| "learning_rate": 2.7000000000000002e-05, |
| "loss": 0.0403, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.56, |
| "grad_norm": 3.254148006439209, |
| "learning_rate": 2.8000000000000003e-05, |
| "loss": 0.0218, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.58, |
| "grad_norm": 2.123260498046875, |
| "learning_rate": 2.9e-05, |
| "loss": 0.0449, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 1.0731960535049438, |
| "learning_rate": 3e-05, |
| "loss": 0.0222, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.62, |
| "grad_norm": 0.8489921689033508, |
| "learning_rate": 3.1e-05, |
| "loss": 0.0149, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.64, |
| "grad_norm": 0.589127779006958, |
| "learning_rate": 3.2000000000000005e-05, |
| "loss": 0.022, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.66, |
| "grad_norm": 0.42175689339637756, |
| "learning_rate": 3.3e-05, |
| "loss": 0.0109, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.68, |
| "grad_norm": 0.19729836285114288, |
| "learning_rate": 3.4000000000000007e-05, |
| "loss": 0.0093, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.7, |
| "grad_norm": 0.2009144425392151, |
| "learning_rate": 3.5e-05, |
| "loss": 0.0087, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.72, |
| "grad_norm": 0.2093500941991806, |
| "learning_rate": 3.6e-05, |
| "loss": 0.0079, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.74, |
| "grad_norm": 0.1865512728691101, |
| "learning_rate": 3.7e-05, |
| "loss": 0.0072, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.76, |
| "grad_norm": 0.18552368879318237, |
| "learning_rate": 3.8e-05, |
| "loss": 0.0065, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.78, |
| "grad_norm": 0.17754022777080536, |
| "learning_rate": 3.9000000000000006e-05, |
| "loss": 0.0058, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.1693771779537201, |
| "learning_rate": 4e-05, |
| "loss": 0.005, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.82, |
| "grad_norm": 0.156035915017128, |
| "learning_rate": 4.1e-05, |
| "loss": 0.0042, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.84, |
| "grad_norm": 0.13963238894939423, |
| "learning_rate": 4.2e-05, |
| "loss": 0.0035, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.86, |
| "grad_norm": 0.12009837478399277, |
| "learning_rate": 4.3e-05, |
| "loss": 0.0029, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.88, |
| "grad_norm": 0.09549227356910706, |
| "learning_rate": 4.4000000000000006e-05, |
| "loss": 0.0024, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.9, |
| "grad_norm": 0.07229408621788025, |
| "learning_rate": 4.5e-05, |
| "loss": 0.002, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.92, |
| "grad_norm": 0.05505015328526497, |
| "learning_rate": 4.600000000000001e-05, |
| "loss": 0.0018, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.94, |
| "grad_norm": 0.038959477096796036, |
| "learning_rate": 4.7e-05, |
| "loss": 0.0016, |
| "step": 47 |
| }, |
| { |
| "epoch": 0.96, |
| "grad_norm": 0.029499763622879982, |
| "learning_rate": 4.8e-05, |
| "loss": 0.0015, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.98, |
| "grad_norm": 0.026312170550227165, |
| "learning_rate": 4.9e-05, |
| "loss": 0.0014, |
| "step": 49 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.020306073129177094, |
| "learning_rate": 5e-05, |
| "loss": 0.0014, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.02, |
| "grad_norm": 0.014265279285609722, |
| "learning_rate": 4.999939076763487e-05, |
| "loss": 0.0013, |
| "step": 51 |
| }, |
| { |
| "epoch": 1.04, |
| "grad_norm": 0.02053067646920681, |
| "learning_rate": 4.999756310023261e-05, |
| "loss": 0.0013, |
| "step": 52 |
| }, |
| { |
| "epoch": 1.06, |
| "grad_norm": 0.015466387383639812, |
| "learning_rate": 4.999451708687114e-05, |
| "loss": 0.0013, |
| "step": 53 |
| }, |
| { |
| "epoch": 1.08, |
| "grad_norm": 0.015973195433616638, |
| "learning_rate": 4.999025287600886e-05, |
| "loss": 0.0012, |
| "step": 54 |
| }, |
| { |
| "epoch": 1.1, |
| "grad_norm": 0.008490358479321003, |
| "learning_rate": 4.99847706754774e-05, |
| "loss": 0.0012, |
| "step": 55 |
| }, |
| { |
| "epoch": 1.12, |
| "grad_norm": 0.012946813367307186, |
| "learning_rate": 4.997807075247146e-05, |
| "loss": 0.0012, |
| "step": 56 |
| }, |
| { |
| "epoch": 1.1400000000000001, |
| "grad_norm": 0.01698051020503044, |
| "learning_rate": 4.997015343353585e-05, |
| "loss": 0.0013, |
| "step": 57 |
| }, |
| { |
| "epoch": 1.16, |
| "grad_norm": 0.013274472206830978, |
| "learning_rate": 4.996101910454953e-05, |
| "loss": 0.0012, |
| "step": 58 |
| }, |
| { |
| "epoch": 1.18, |
| "grad_norm": 0.01776733063161373, |
| "learning_rate": 4.995066821070679e-05, |
| "loss": 0.0012, |
| "step": 59 |
| }, |
| { |
| "epoch": 1.2, |
| "grad_norm": 0.015046725980937481, |
| "learning_rate": 4.993910125649561e-05, |
| "loss": 0.0012, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.22, |
| "grad_norm": 0.014767763204872608, |
| "learning_rate": 4.992631880567301e-05, |
| "loss": 0.0011, |
| "step": 61 |
| }, |
| { |
| "epoch": 1.24, |
| "grad_norm": 0.007155032362788916, |
| "learning_rate": 4.991232148123761e-05, |
| "loss": 0.0012, |
| "step": 62 |
| }, |
| { |
| "epoch": 1.26, |
| "grad_norm": 0.01570066623389721, |
| "learning_rate": 4.989710996539926e-05, |
| "loss": 0.0012, |
| "step": 63 |
| }, |
| { |
| "epoch": 1.28, |
| "grad_norm": 0.019080698490142822, |
| "learning_rate": 4.988068499954578e-05, |
| "loss": 0.0012, |
| "step": 64 |
| }, |
| { |
| "epoch": 1.3, |
| "grad_norm": 0.016244422644376755, |
| "learning_rate": 4.9863047384206835e-05, |
| "loss": 0.0011, |
| "step": 65 |
| }, |
| { |
| "epoch": 1.32, |
| "grad_norm": 0.06490402668714523, |
| "learning_rate": 4.984419797901491e-05, |
| "loss": 0.0013, |
| "step": 66 |
| }, |
| { |
| "epoch": 1.34, |
| "grad_norm": 0.02592933550477028, |
| "learning_rate": 4.982413770266342e-05, |
| "loss": 0.0012, |
| "step": 67 |
| }, |
| { |
| "epoch": 1.3599999999999999, |
| "grad_norm": 0.01940583623945713, |
| "learning_rate": 4.980286753286195e-05, |
| "loss": 0.0012, |
| "step": 68 |
| }, |
| { |
| "epoch": 1.38, |
| "grad_norm": 0.016211828216910362, |
| "learning_rate": 4.978038850628854e-05, |
| "loss": 0.0012, |
| "step": 69 |
| }, |
| { |
| "epoch": 1.4, |
| "grad_norm": 0.018053313717246056, |
| "learning_rate": 4.975670171853926e-05, |
| "loss": 0.0012, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.42, |
| "grad_norm": 0.01438748836517334, |
| "learning_rate": 4.9731808324074717e-05, |
| "loss": 0.0012, |
| "step": 71 |
| }, |
| { |
| "epoch": 1.44, |
| "grad_norm": 0.011617658659815788, |
| "learning_rate": 4.9705709536163824e-05, |
| "loss": 0.0012, |
| "step": 72 |
| }, |
| { |
| "epoch": 1.46, |
| "grad_norm": 0.007649057544767857, |
| "learning_rate": 4.96784066268247e-05, |
| "loss": 0.0012, |
| "step": 73 |
| }, |
| { |
| "epoch": 1.48, |
| "grad_norm": 0.0060863615944981575, |
| "learning_rate": 4.964990092676263e-05, |
| "loss": 0.0012, |
| "step": 74 |
| }, |
| { |
| "epoch": 1.5, |
| "grad_norm": 0.011736256070435047, |
| "learning_rate": 4.962019382530521e-05, |
| "loss": 0.0012, |
| "step": 75 |
| }, |
| { |
| "epoch": 1.52, |
| "grad_norm": 0.00740490248426795, |
| "learning_rate": 4.9589286770334654e-05, |
| "loss": 0.0012, |
| "step": 76 |
| }, |
| { |
| "epoch": 1.54, |
| "grad_norm": 0.008237659931182861, |
| "learning_rate": 4.9557181268217227e-05, |
| "loss": 0.0012, |
| "step": 77 |
| }, |
| { |
| "epoch": 1.56, |
| "grad_norm": 0.005937286652624607, |
| "learning_rate": 4.952387888372979e-05, |
| "loss": 0.0012, |
| "step": 78 |
| }, |
| { |
| "epoch": 1.58, |
| "grad_norm": 0.010778284631669521, |
| "learning_rate": 4.94893812399836e-05, |
| "loss": 0.0012, |
| "step": 79 |
| }, |
| { |
| "epoch": 1.6, |
| "grad_norm": 0.005073127802461386, |
| "learning_rate": 4.9453690018345144e-05, |
| "loss": 0.0012, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.62, |
| "grad_norm": 0.015029042027890682, |
| "learning_rate": 4.94168069583542e-05, |
| "loss": 0.0012, |
| "step": 81 |
| }, |
| { |
| "epoch": 1.6400000000000001, |
| "grad_norm": 0.003979986067861319, |
| "learning_rate": 4.937873385763908e-05, |
| "loss": 0.0012, |
| "step": 82 |
| }, |
| { |
| "epoch": 1.6600000000000001, |
| "grad_norm": 0.005284400191158056, |
| "learning_rate": 4.933947257182901e-05, |
| "loss": 0.0012, |
| "step": 83 |
| }, |
| { |
| "epoch": 1.6800000000000002, |
| "grad_norm": 0.0076846531592309475, |
| "learning_rate": 4.929902501446366e-05, |
| "loss": 0.0012, |
| "step": 84 |
| }, |
| { |
| "epoch": 1.7, |
| "grad_norm": 0.006414446514099836, |
| "learning_rate": 4.925739315689991e-05, |
| "loss": 0.0012, |
| "step": 85 |
| }, |
| { |
| "epoch": 1.72, |
| "grad_norm": 0.005861522629857063, |
| "learning_rate": 4.9214579028215776e-05, |
| "loss": 0.0012, |
| "step": 86 |
| }, |
| { |
| "epoch": 1.74, |
| "grad_norm": 0.007500852923840284, |
| "learning_rate": 4.917058471511149e-05, |
| "loss": 0.0012, |
| "step": 87 |
| }, |
| { |
| "epoch": 1.76, |
| "grad_norm": 0.010749063454568386, |
| "learning_rate": 4.912541236180779e-05, |
| "loss": 0.0012, |
| "step": 88 |
| }, |
| { |
| "epoch": 1.78, |
| "grad_norm": 0.01243392564356327, |
| "learning_rate": 4.907906416994146e-05, |
| "loss": 0.0012, |
| "step": 89 |
| }, |
| { |
| "epoch": 1.8, |
| "grad_norm": 0.006575236562639475, |
| "learning_rate": 4.9031542398457974e-05, |
| "loss": 0.0011, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.8199999999999998, |
| "grad_norm": 0.018216770142316818, |
| "learning_rate": 4.898284936350144e-05, |
| "loss": 0.0012, |
| "step": 91 |
| }, |
| { |
| "epoch": 1.8399999999999999, |
| "grad_norm": 0.009646720252931118, |
| "learning_rate": 4.893298743830168e-05, |
| "loss": 0.0011, |
| "step": 92 |
| }, |
| { |
| "epoch": 1.8599999999999999, |
| "grad_norm": 0.00471867062151432, |
| "learning_rate": 4.888195905305859e-05, |
| "loss": 0.0011, |
| "step": 93 |
| }, |
| { |
| "epoch": 1.88, |
| "grad_norm": 0.010674097575247288, |
| "learning_rate": 4.882976669482367e-05, |
| "loss": 0.0011, |
| "step": 94 |
| }, |
| { |
| "epoch": 1.9, |
| "grad_norm": 0.010026497766375542, |
| "learning_rate": 4.877641290737884e-05, |
| "loss": 0.0011, |
| "step": 95 |
| }, |
| { |
| "epoch": 1.92, |
| "grad_norm": 0.01685321517288685, |
| "learning_rate": 4.8721900291112415e-05, |
| "loss": 0.0011, |
| "step": 96 |
| }, |
| { |
| "epoch": 1.94, |
| "grad_norm": 0.015050926245748997, |
| "learning_rate": 4.8666231502892415e-05, |
| "loss": 0.0011, |
| "step": 97 |
| }, |
| { |
| "epoch": 1.96, |
| "grad_norm": 0.008265609852969646, |
| "learning_rate": 4.860940925593703e-05, |
| "loss": 0.0011, |
| "step": 98 |
| }, |
| { |
| "epoch": 1.98, |
| "grad_norm": 0.022018827497959137, |
| "learning_rate": 4.855143631968242e-05, |
| "loss": 0.0012, |
| "step": 99 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.01330670714378357, |
| "learning_rate": 4.849231551964771e-05, |
| "loss": 0.001, |
| "step": 100 |
| }, |
| { |
| "epoch": 2.02, |
| "grad_norm": 0.030819913372397423, |
| "learning_rate": 4.843204973729729e-05, |
| "loss": 0.0011, |
| "step": 101 |
| }, |
| { |
| "epoch": 2.04, |
| "grad_norm": 0.018151411786675453, |
| "learning_rate": 4.837064190990036e-05, |
| "loss": 0.001, |
| "step": 102 |
| }, |
| { |
| "epoch": 2.06, |
| "grad_norm": 0.022368013858795166, |
| "learning_rate": 4.830809503038781e-05, |
| "loss": 0.0011, |
| "step": 103 |
| }, |
| { |
| "epoch": 2.08, |
| "grad_norm": 0.0231326837092638, |
| "learning_rate": 4.8244412147206284e-05, |
| "loss": 0.0011, |
| "step": 104 |
| }, |
| { |
| "epoch": 2.1, |
| "grad_norm": 0.01942342147231102, |
| "learning_rate": 4.817959636416969e-05, |
| "loss": 0.001, |
| "step": 105 |
| }, |
| { |
| "epoch": 2.12, |
| "grad_norm": 0.025518309324979782, |
| "learning_rate": 4.8113650840307834e-05, |
| "loss": 0.001, |
| "step": 106 |
| }, |
| { |
| "epoch": 2.14, |
| "grad_norm": 0.01907534897327423, |
| "learning_rate": 4.8046578789712515e-05, |
| "loss": 0.001, |
| "step": 107 |
| }, |
| { |
| "epoch": 2.16, |
| "grad_norm": 0.06474534422159195, |
| "learning_rate": 4.797838348138086e-05, |
| "loss": 0.0012, |
| "step": 108 |
| }, |
| { |
| "epoch": 2.18, |
| "grad_norm": 0.014870468527078629, |
| "learning_rate": 4.790906823905599e-05, |
| "loss": 0.001, |
| "step": 109 |
| }, |
| { |
| "epoch": 2.2, |
| "grad_norm": 0.033130887895822525, |
| "learning_rate": 4.783863644106502e-05, |
| "loss": 0.0012, |
| "step": 110 |
| }, |
| { |
| "epoch": 2.22, |
| "grad_norm": 0.021351227536797523, |
| "learning_rate": 4.776709152015443e-05, |
| "loss": 0.0011, |
| "step": 111 |
| }, |
| { |
| "epoch": 2.24, |
| "grad_norm": 0.017795074731111526, |
| "learning_rate": 4.769443696332272e-05, |
| "loss": 0.0009, |
| "step": 112 |
| }, |
| { |
| "epoch": 2.26, |
| "grad_norm": 0.014288947917521, |
| "learning_rate": 4.762067631165049e-05, |
| "loss": 0.001, |
| "step": 113 |
| }, |
| { |
| "epoch": 2.2800000000000002, |
| "grad_norm": 0.019312620162963867, |
| "learning_rate": 4.754581316012785e-05, |
| "loss": 0.001, |
| "step": 114 |
| }, |
| { |
| "epoch": 2.3, |
| "grad_norm": 0.015632573515176773, |
| "learning_rate": 4.7469851157479177e-05, |
| "loss": 0.001, |
| "step": 115 |
| }, |
| { |
| "epoch": 2.32, |
| "grad_norm": 0.012786476872861385, |
| "learning_rate": 4.7392794005985326e-05, |
| "loss": 0.001, |
| "step": 116 |
| }, |
| { |
| "epoch": 2.34, |
| "grad_norm": 0.042442597448825836, |
| "learning_rate": 4.731464546130314e-05, |
| "loss": 0.001, |
| "step": 117 |
| }, |
| { |
| "epoch": 2.36, |
| "grad_norm": 0.021612655371427536, |
| "learning_rate": 4.723540933228244e-05, |
| "loss": 0.0009, |
| "step": 118 |
| }, |
| { |
| "epoch": 2.38, |
| "grad_norm": 0.022924797609448433, |
| "learning_rate": 4.715508948078037e-05, |
| "loss": 0.001, |
| "step": 119 |
| }, |
| { |
| "epoch": 2.4, |
| "grad_norm": 0.025588147342205048, |
| "learning_rate": 4.707368982147318e-05, |
| "loss": 0.0009, |
| "step": 120 |
| }, |
| { |
| "epoch": 2.42, |
| "grad_norm": 0.01950550638139248, |
| "learning_rate": 4.6991214321665414e-05, |
| "loss": 0.0009, |
| "step": 121 |
| }, |
| { |
| "epoch": 2.44, |
| "grad_norm": 0.027708236128091812, |
| "learning_rate": 4.690766700109659e-05, |
| "loss": 0.001, |
| "step": 122 |
| }, |
| { |
| "epoch": 2.46, |
| "grad_norm": 0.032382309436798096, |
| "learning_rate": 4.682305193174524e-05, |
| "loss": 0.0009, |
| "step": 123 |
| }, |
| { |
| "epoch": 2.48, |
| "grad_norm": 0.02310575172305107, |
| "learning_rate": 4.6737373237630476e-05, |
| "loss": 0.001, |
| "step": 124 |
| }, |
| { |
| "epoch": 2.5, |
| "grad_norm": 0.04070095717906952, |
| "learning_rate": 4.665063509461097e-05, |
| "loss": 0.0009, |
| "step": 125 |
| }, |
| { |
| "epoch": 2.52, |
| "grad_norm": 0.041273683309555054, |
| "learning_rate": 4.656284173018144e-05, |
| "loss": 0.001, |
| "step": 126 |
| }, |
| { |
| "epoch": 2.54, |
| "grad_norm": 0.014590524137020111, |
| "learning_rate": 4.6473997423266614e-05, |
| "loss": 0.0009, |
| "step": 127 |
| }, |
| { |
| "epoch": 2.56, |
| "grad_norm": 0.02202373370528221, |
| "learning_rate": 4.638410650401267e-05, |
| "loss": 0.001, |
| "step": 128 |
| }, |
| { |
| "epoch": 2.58, |
| "grad_norm": 0.015360541641712189, |
| "learning_rate": 4.629317335357619e-05, |
| "loss": 0.001, |
| "step": 129 |
| }, |
| { |
| "epoch": 2.6, |
| "grad_norm": 0.01654900051653385, |
| "learning_rate": 4.620120240391065e-05, |
| "loss": 0.001, |
| "step": 130 |
| }, |
| { |
| "epoch": 2.62, |
| "grad_norm": 0.01125663798302412, |
| "learning_rate": 4.610819813755038e-05, |
| "loss": 0.001, |
| "step": 131 |
| }, |
| { |
| "epoch": 2.64, |
| "grad_norm": 0.012902496382594109, |
| "learning_rate": 4.601416508739211e-05, |
| "loss": 0.0009, |
| "step": 132 |
| }, |
| { |
| "epoch": 2.66, |
| "grad_norm": 0.0195336751639843, |
| "learning_rate": 4.591910783647404e-05, |
| "loss": 0.0011, |
| "step": 133 |
| }, |
| { |
| "epoch": 2.68, |
| "grad_norm": 0.02390046790242195, |
| "learning_rate": 4.5823031017752485e-05, |
| "loss": 0.0011, |
| "step": 134 |
| }, |
| { |
| "epoch": 2.7, |
| "grad_norm": 0.014201649464666843, |
| "learning_rate": 4.572593931387604e-05, |
| "loss": 0.0009, |
| "step": 135 |
| }, |
| { |
| "epoch": 2.7199999999999998, |
| "grad_norm": 0.012115216813981533, |
| "learning_rate": 4.562783745695738e-05, |
| "loss": 0.0009, |
| "step": 136 |
| }, |
| { |
| "epoch": 2.74, |
| "grad_norm": 0.022056447342038155, |
| "learning_rate": 4.5528730228342605e-05, |
| "loss": 0.0009, |
| "step": 137 |
| }, |
| { |
| "epoch": 2.76, |
| "grad_norm": 0.019029831513762474, |
| "learning_rate": 4.542862245837821e-05, |
| "loss": 0.001, |
| "step": 138 |
| }, |
| { |
| "epoch": 2.7800000000000002, |
| "grad_norm": 0.020401952788233757, |
| "learning_rate": 4.532751902617569e-05, |
| "loss": 0.0009, |
| "step": 139 |
| }, |
| { |
| "epoch": 2.8, |
| "grad_norm": 0.018967969343066216, |
| "learning_rate": 4.522542485937369e-05, |
| "loss": 0.0009, |
| "step": 140 |
| }, |
| { |
| "epoch": 2.82, |
| "grad_norm": 0.034043021500110626, |
| "learning_rate": 4.512234493389785e-05, |
| "loss": 0.0011, |
| "step": 141 |
| }, |
| { |
| "epoch": 2.84, |
| "grad_norm": 0.02043725550174713, |
| "learning_rate": 4.5018284273718336e-05, |
| "loss": 0.001, |
| "step": 142 |
| }, |
| { |
| "epoch": 2.86, |
| "grad_norm": 0.014444992877542973, |
| "learning_rate": 4.491324795060491e-05, |
| "loss": 0.0009, |
| "step": 143 |
| }, |
| { |
| "epoch": 2.88, |
| "grad_norm": 0.015194895677268505, |
| "learning_rate": 4.480724108387977e-05, |
| "loss": 0.0009, |
| "step": 144 |
| }, |
| { |
| "epoch": 2.9, |
| "grad_norm": 0.010989692993462086, |
| "learning_rate": 4.4700268840168045e-05, |
| "loss": 0.0009, |
| "step": 145 |
| }, |
| { |
| "epoch": 2.92, |
| "grad_norm": 0.026291556656360626, |
| "learning_rate": 4.4592336433146e-05, |
| "loss": 0.001, |
| "step": 146 |
| }, |
| { |
| "epoch": 2.94, |
| "grad_norm": 0.015329469926655293, |
| "learning_rate": 4.448344912328686e-05, |
| "loss": 0.0009, |
| "step": 147 |
| }, |
| { |
| "epoch": 2.96, |
| "grad_norm": 0.013111543841660023, |
| "learning_rate": 4.4373612217604496e-05, |
| "loss": 0.001, |
| "step": 148 |
| }, |
| { |
| "epoch": 2.98, |
| "grad_norm": 0.013395372778177261, |
| "learning_rate": 4.426283106939474e-05, |
| "loss": 0.0009, |
| "step": 149 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.013448159210383892, |
| "learning_rate": 4.415111107797445e-05, |
| "loss": 0.0008, |
| "step": 150 |
| }, |
| { |
| "epoch": 3.02, |
| "grad_norm": 0.01918015442788601, |
| "learning_rate": 4.403845768841842e-05, |
| "loss": 0.0009, |
| "step": 151 |
| }, |
| { |
| "epoch": 3.04, |
| "grad_norm": 0.017055032774806023, |
| "learning_rate": 4.3924876391293915e-05, |
| "loss": 0.0009, |
| "step": 152 |
| }, |
| { |
| "epoch": 3.06, |
| "grad_norm": 0.006383760366588831, |
| "learning_rate": 4.381037272239311e-05, |
| "loss": 0.0009, |
| "step": 153 |
| }, |
| { |
| "epoch": 3.08, |
| "grad_norm": 0.016412733122706413, |
| "learning_rate": 4.36949522624633e-05, |
| "loss": 0.0009, |
| "step": 154 |
| }, |
| { |
| "epoch": 3.1, |
| "grad_norm": 0.01369386911392212, |
| "learning_rate": 4.357862063693486e-05, |
| "loss": 0.0009, |
| "step": 155 |
| }, |
| { |
| "epoch": 3.12, |
| "grad_norm": 0.01586688682436943, |
| "learning_rate": 4.3461383515647106e-05, |
| "loss": 0.001, |
| "step": 156 |
| }, |
| { |
| "epoch": 3.14, |
| "grad_norm": 0.009514207020401955, |
| "learning_rate": 4.334324661257191e-05, |
| "loss": 0.0008, |
| "step": 157 |
| }, |
| { |
| "epoch": 3.16, |
| "grad_norm": 0.011565557681024075, |
| "learning_rate": 4.3224215685535294e-05, |
| "loss": 0.0009, |
| "step": 158 |
| }, |
| { |
| "epoch": 3.18, |
| "grad_norm": 0.01942281424999237, |
| "learning_rate": 4.3104296535936695e-05, |
| "loss": 0.001, |
| "step": 159 |
| }, |
| { |
| "epoch": 3.2, |
| "grad_norm": 0.025319915264844894, |
| "learning_rate": 4.2983495008466276e-05, |
| "loss": 0.001, |
| "step": 160 |
| }, |
| { |
| "epoch": 3.22, |
| "grad_norm": 0.020152214914560318, |
| "learning_rate": 4.2861816990820084e-05, |
| "loss": 0.0009, |
| "step": 161 |
| }, |
| { |
| "epoch": 3.24, |
| "grad_norm": 0.014544936828315258, |
| "learning_rate": 4.273926841341302e-05, |
| "loss": 0.0009, |
| "step": 162 |
| }, |
| { |
| "epoch": 3.26, |
| "grad_norm": 0.013562367297708988, |
| "learning_rate": 4.261585524908987e-05, |
| "loss": 0.0009, |
| "step": 163 |
| }, |
| { |
| "epoch": 3.2800000000000002, |
| "grad_norm": 0.016432832926511765, |
| "learning_rate": 4.249158351283414e-05, |
| "loss": 0.001, |
| "step": 164 |
| }, |
| { |
| "epoch": 3.3, |
| "grad_norm": 0.01196199283003807, |
| "learning_rate": 4.2366459261474933e-05, |
| "loss": 0.0009, |
| "step": 165 |
| }, |
| { |
| "epoch": 3.32, |
| "grad_norm": 0.012741833925247192, |
| "learning_rate": 4.224048859339175e-05, |
| "loss": 0.0009, |
| "step": 166 |
| }, |
| { |
| "epoch": 3.34, |
| "grad_norm": 0.015541434288024902, |
| "learning_rate": 4.211367764821722e-05, |
| "loss": 0.0008, |
| "step": 167 |
| }, |
| { |
| "epoch": 3.36, |
| "grad_norm": 0.010746212676167488, |
| "learning_rate": 4.198603260653792e-05, |
| "loss": 0.0009, |
| "step": 168 |
| }, |
| { |
| "epoch": 3.38, |
| "grad_norm": 0.014585288241505623, |
| "learning_rate": 4.185755968959308e-05, |
| "loss": 0.0009, |
| "step": 169 |
| }, |
| { |
| "epoch": 3.4, |
| "grad_norm": 0.009942736476659775, |
| "learning_rate": 4.172826515897146e-05, |
| "loss": 0.0009, |
| "step": 170 |
| }, |
| { |
| "epoch": 3.42, |
| "grad_norm": 0.017286481335759163, |
| "learning_rate": 4.1598155316306044e-05, |
| "loss": 0.0009, |
| "step": 171 |
| }, |
| { |
| "epoch": 3.44, |
| "grad_norm": 0.013385478407144547, |
| "learning_rate": 4.146723650296701e-05, |
| "loss": 0.0008, |
| "step": 172 |
| }, |
| { |
| "epoch": 3.46, |
| "grad_norm": 0.05108925700187683, |
| "learning_rate": 4.133551509975264e-05, |
| "loss": 0.0009, |
| "step": 173 |
| }, |
| { |
| "epoch": 3.48, |
| "grad_norm": 0.013413962908089161, |
| "learning_rate": 4.1202997526578276e-05, |
| "loss": 0.0008, |
| "step": 174 |
| }, |
| { |
| "epoch": 3.5, |
| "grad_norm": 0.010358484461903572, |
| "learning_rate": 4.1069690242163484e-05, |
| "loss": 0.0008, |
| "step": 175 |
| }, |
| { |
| "epoch": 3.52, |
| "grad_norm": 0.013632961548864841, |
| "learning_rate": 4.093559974371725e-05, |
| "loss": 0.0008, |
| "step": 176 |
| }, |
| { |
| "epoch": 3.54, |
| "grad_norm": 0.009852699935436249, |
| "learning_rate": 4.080073256662127e-05, |
| "loss": 0.0009, |
| "step": 177 |
| }, |
| { |
| "epoch": 3.56, |
| "grad_norm": 0.007956922985613346, |
| "learning_rate": 4.066509528411152e-05, |
| "loss": 0.0009, |
| "step": 178 |
| }, |
| { |
| "epoch": 3.58, |
| "grad_norm": 0.016999222338199615, |
| "learning_rate": 4.052869450695776e-05, |
| "loss": 0.001, |
| "step": 179 |
| }, |
| { |
| "epoch": 3.6, |
| "grad_norm": 0.013647818006575108, |
| "learning_rate": 4.039153688314145e-05, |
| "loss": 0.001, |
| "step": 180 |
| }, |
| { |
| "epoch": 3.62, |
| "grad_norm": 0.012612687423825264, |
| "learning_rate": 4.02536290975317e-05, |
| "loss": 0.0008, |
| "step": 181 |
| }, |
| { |
| "epoch": 3.64, |
| "grad_norm": 0.01253987941890955, |
| "learning_rate": 4.011497787155938e-05, |
| "loss": 0.0008, |
| "step": 182 |
| }, |
| { |
| "epoch": 3.66, |
| "grad_norm": 0.01009274460375309, |
| "learning_rate": 3.997558996288965e-05, |
| "loss": 0.0009, |
| "step": 183 |
| }, |
| { |
| "epoch": 3.68, |
| "grad_norm": 0.012114924378693104, |
| "learning_rate": 3.983547216509254e-05, |
| "loss": 0.0009, |
| "step": 184 |
| }, |
| { |
| "epoch": 3.7, |
| "grad_norm": 0.00788212101906538, |
| "learning_rate": 3.969463130731183e-05, |
| "loss": 0.0008, |
| "step": 185 |
| }, |
| { |
| "epoch": 3.7199999999999998, |
| "grad_norm": 0.009055244736373425, |
| "learning_rate": 3.955307425393224e-05, |
| "loss": 0.0007, |
| "step": 186 |
| }, |
| { |
| "epoch": 3.74, |
| "grad_norm": 0.015629315748810768, |
| "learning_rate": 3.941080790424484e-05, |
| "loss": 0.0008, |
| "step": 187 |
| }, |
| { |
| "epoch": 3.76, |
| "grad_norm": 0.012710140086710453, |
| "learning_rate": 3.92678391921108e-05, |
| "loss": 0.0008, |
| "step": 188 |
| }, |
| { |
| "epoch": 3.7800000000000002, |
| "grad_norm": 0.013408125378191471, |
| "learning_rate": 3.912417508562345e-05, |
| "loss": 0.0008, |
| "step": 189 |
| }, |
| { |
| "epoch": 3.8, |
| "grad_norm": 0.012659719213843346, |
| "learning_rate": 3.897982258676867e-05, |
| "loss": 0.0008, |
| "step": 190 |
| }, |
| { |
| "epoch": 3.82, |
| "grad_norm": 0.010696173645555973, |
| "learning_rate": 3.883478873108361e-05, |
| "loss": 0.0008, |
| "step": 191 |
| }, |
| { |
| "epoch": 3.84, |
| "grad_norm": 0.01534357201308012, |
| "learning_rate": 3.868908058731376e-05, |
| "loss": 0.0007, |
| "step": 192 |
| }, |
| { |
| "epoch": 3.86, |
| "grad_norm": 0.021090975031256676, |
| "learning_rate": 3.85427052570685e-05, |
| "loss": 0.001, |
| "step": 193 |
| }, |
| { |
| "epoch": 3.88, |
| "grad_norm": 0.007561246864497662, |
| "learning_rate": 3.8395669874474915e-05, |
| "loss": 0.0007, |
| "step": 194 |
| }, |
| { |
| "epoch": 3.9, |
| "grad_norm": 0.035602714866399765, |
| "learning_rate": 3.824798160583012e-05, |
| "loss": 0.0009, |
| "step": 195 |
| }, |
| { |
| "epoch": 3.92, |
| "grad_norm": 0.012646924704313278, |
| "learning_rate": 3.8099647649251986e-05, |
| "loss": 0.0007, |
| "step": 196 |
| }, |
| { |
| "epoch": 3.94, |
| "grad_norm": 0.018672510981559753, |
| "learning_rate": 3.795067523432826e-05, |
| "loss": 0.001, |
| "step": 197 |
| }, |
| { |
| "epoch": 3.96, |
| "grad_norm": 0.03359285369515419, |
| "learning_rate": 3.780107162176429e-05, |
| "loss": 0.0009, |
| "step": 198 |
| }, |
| { |
| "epoch": 3.98, |
| "grad_norm": 0.008940763771533966, |
| "learning_rate": 3.765084410302909e-05, |
| "loss": 0.0008, |
| "step": 199 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.013762730173766613, |
| "learning_rate": 3.7500000000000003e-05, |
| "loss": 0.0009, |
| "step": 200 |
| }, |
| { |
| "epoch": 4.02, |
| "grad_norm": 0.01622450351715088, |
| "learning_rate": 3.7348546664605777e-05, |
| "loss": 0.0008, |
| "step": 201 |
| }, |
| { |
| "epoch": 4.04, |
| "grad_norm": 0.017409563064575195, |
| "learning_rate": 3.719649147846832e-05, |
| "loss": 0.0009, |
| "step": 202 |
| }, |
| { |
| "epoch": 4.06, |
| "grad_norm": 0.011531161144375801, |
| "learning_rate": 3.704384185254288e-05, |
| "loss": 0.0008, |
| "step": 203 |
| }, |
| { |
| "epoch": 4.08, |
| "grad_norm": 0.00890585407614708, |
| "learning_rate": 3.689060522675689e-05, |
| "loss": 0.0008, |
| "step": 204 |
| }, |
| { |
| "epoch": 4.1, |
| "grad_norm": 0.009238718077540398, |
| "learning_rate": 3.673678906964727e-05, |
| "loss": 0.0008, |
| "step": 205 |
| }, |
| { |
| "epoch": 4.12, |
| "grad_norm": 0.011698647402226925, |
| "learning_rate": 3.6582400877996546e-05, |
| "loss": 0.0008, |
| "step": 206 |
| }, |
| { |
| "epoch": 4.14, |
| "grad_norm": 0.0154410470277071, |
| "learning_rate": 3.642744817646736e-05, |
| "loss": 0.0008, |
| "step": 207 |
| }, |
| { |
| "epoch": 4.16, |
| "grad_norm": 0.02395373024046421, |
| "learning_rate": 3.627193851723577e-05, |
| "loss": 0.0007, |
| "step": 208 |
| }, |
| { |
| "epoch": 4.18, |
| "grad_norm": 0.014127401635050774, |
| "learning_rate": 3.611587947962319e-05, |
| "loss": 0.0009, |
| "step": 209 |
| }, |
| { |
| "epoch": 4.2, |
| "grad_norm": 0.016634410247206688, |
| "learning_rate": 3.5959278669726935e-05, |
| "loss": 0.0009, |
| "step": 210 |
| }, |
| { |
| "epoch": 4.22, |
| "grad_norm": 0.026153067126870155, |
| "learning_rate": 3.580214372004956e-05, |
| "loss": 0.0008, |
| "step": 211 |
| }, |
| { |
| "epoch": 4.24, |
| "grad_norm": 0.035530734807252884, |
| "learning_rate": 3.564448228912682e-05, |
| "loss": 0.0008, |
| "step": 212 |
| }, |
| { |
| "epoch": 4.26, |
| "grad_norm": 0.014608434401452541, |
| "learning_rate": 3.548630206115443e-05, |
| "loss": 0.0007, |
| "step": 213 |
| }, |
| { |
| "epoch": 4.28, |
| "grad_norm": 0.016531968489289284, |
| "learning_rate": 3.532761074561355e-05, |
| "loss": 0.0009, |
| "step": 214 |
| }, |
| { |
| "epoch": 4.3, |
| "grad_norm": 0.00973664689809084, |
| "learning_rate": 3.516841607689501e-05, |
| "loss": 0.0007, |
| "step": 215 |
| }, |
| { |
| "epoch": 4.32, |
| "grad_norm": 0.01250792108476162, |
| "learning_rate": 3.5008725813922386e-05, |
| "loss": 0.0007, |
| "step": 216 |
| }, |
| { |
| "epoch": 4.34, |
| "grad_norm": 0.021898312494158745, |
| "learning_rate": 3.484854773977378e-05, |
| "loss": 0.0007, |
| "step": 217 |
| }, |
| { |
| "epoch": 4.36, |
| "grad_norm": 0.04025641456246376, |
| "learning_rate": 3.4687889661302576e-05, |
| "loss": 0.0008, |
| "step": 218 |
| }, |
| { |
| "epoch": 4.38, |
| "grad_norm": 0.015246308408677578, |
| "learning_rate": 3.452675940875686e-05, |
| "loss": 0.0008, |
| "step": 219 |
| }, |
| { |
| "epoch": 4.4, |
| "grad_norm": 0.010531401261687279, |
| "learning_rate": 3.436516483539781e-05, |
| "loss": 0.0007, |
| "step": 220 |
| }, |
| { |
| "epoch": 4.42, |
| "grad_norm": 0.014213008806109428, |
| "learning_rate": 3.4203113817116957e-05, |
| "loss": 0.0007, |
| "step": 221 |
| }, |
| { |
| "epoch": 4.44, |
| "grad_norm": 0.035328883677721024, |
| "learning_rate": 3.4040614252052305e-05, |
| "loss": 0.0008, |
| "step": 222 |
| }, |
| { |
| "epoch": 4.46, |
| "grad_norm": 0.019592702388763428, |
| "learning_rate": 3.387767406020343e-05, |
| "loss": 0.0008, |
| "step": 223 |
| }, |
| { |
| "epoch": 4.48, |
| "grad_norm": 0.014544193632900715, |
| "learning_rate": 3.3714301183045385e-05, |
| "loss": 0.0007, |
| "step": 224 |
| }, |
| { |
| "epoch": 4.5, |
| "grad_norm": 0.01257528830319643, |
| "learning_rate": 3.355050358314172e-05, |
| "loss": 0.0007, |
| "step": 225 |
| }, |
| { |
| "epoch": 4.52, |
| "grad_norm": 0.027983270585536957, |
| "learning_rate": 3.338628924375638e-05, |
| "loss": 0.0006, |
| "step": 226 |
| }, |
| { |
| "epoch": 4.54, |
| "grad_norm": 0.02479342371225357, |
| "learning_rate": 3.322166616846458e-05, |
| "loss": 0.0008, |
| "step": 227 |
| }, |
| { |
| "epoch": 4.5600000000000005, |
| "grad_norm": 0.03580480441451073, |
| "learning_rate": 3.305664238076278e-05, |
| "loss": 0.0008, |
| "step": 228 |
| }, |
| { |
| "epoch": 4.58, |
| "grad_norm": 0.028629954904317856, |
| "learning_rate": 3.289122592367757e-05, |
| "loss": 0.0008, |
| "step": 229 |
| }, |
| { |
| "epoch": 4.6, |
| "grad_norm": 0.029527271166443825, |
| "learning_rate": 3.272542485937369e-05, |
| "loss": 0.0011, |
| "step": 230 |
| }, |
| { |
| "epoch": 4.62, |
| "grad_norm": 0.01633339561522007, |
| "learning_rate": 3.2559247268761115e-05, |
| "loss": 0.0008, |
| "step": 231 |
| }, |
| { |
| "epoch": 4.64, |
| "grad_norm": 0.02296227402985096, |
| "learning_rate": 3.239270125110117e-05, |
| "loss": 0.0008, |
| "step": 232 |
| }, |
| { |
| "epoch": 4.66, |
| "grad_norm": 0.022086285054683685, |
| "learning_rate": 3.222579492361179e-05, |
| "loss": 0.0008, |
| "step": 233 |
| }, |
| { |
| "epoch": 4.68, |
| "grad_norm": 0.015360180288553238, |
| "learning_rate": 3.205853642107192e-05, |
| "loss": 0.0008, |
| "step": 234 |
| }, |
| { |
| "epoch": 4.7, |
| "grad_norm": 0.020640576258301735, |
| "learning_rate": 3.1890933895424976e-05, |
| "loss": 0.0009, |
| "step": 235 |
| }, |
| { |
| "epoch": 4.72, |
| "grad_norm": 0.06557556986808777, |
| "learning_rate": 3.172299551538164e-05, |
| "loss": 0.0009, |
| "step": 236 |
| }, |
| { |
| "epoch": 4.74, |
| "grad_norm": 0.027576349675655365, |
| "learning_rate": 3.155472946602162e-05, |
| "loss": 0.0008, |
| "step": 237 |
| }, |
| { |
| "epoch": 4.76, |
| "grad_norm": 0.019312813878059387, |
| "learning_rate": 3.138614394839476e-05, |
| "loss": 0.0008, |
| "step": 238 |
| }, |
| { |
| "epoch": 4.78, |
| "grad_norm": 0.027863649651408195, |
| "learning_rate": 3.121724717912138e-05, |
| "loss": 0.0009, |
| "step": 239 |
| }, |
| { |
| "epoch": 4.8, |
| "grad_norm": 0.019097020849585533, |
| "learning_rate": 3.104804738999169e-05, |
| "loss": 0.0008, |
| "step": 240 |
| }, |
| { |
| "epoch": 4.82, |
| "grad_norm": 0.025937069207429886, |
| "learning_rate": 3.087855282756475e-05, |
| "loss": 0.0008, |
| "step": 241 |
| }, |
| { |
| "epoch": 4.84, |
| "grad_norm": 0.01815580017864704, |
| "learning_rate": 3.0708771752766394e-05, |
| "loss": 0.0009, |
| "step": 242 |
| }, |
| { |
| "epoch": 4.86, |
| "grad_norm": 0.02074621059000492, |
| "learning_rate": 3.053871244048669e-05, |
| "loss": 0.0008, |
| "step": 243 |
| }, |
| { |
| "epoch": 4.88, |
| "grad_norm": 0.015941645950078964, |
| "learning_rate": 3.0368383179176585e-05, |
| "loss": 0.0008, |
| "step": 244 |
| }, |
| { |
| "epoch": 4.9, |
| "grad_norm": 0.011930015869438648, |
| "learning_rate": 3.0197792270443982e-05, |
| "loss": 0.0007, |
| "step": 245 |
| }, |
| { |
| "epoch": 4.92, |
| "grad_norm": 0.014257809147238731, |
| "learning_rate": 3.002694802864912e-05, |
| "loss": 0.0007, |
| "step": 246 |
| }, |
| { |
| "epoch": 4.9399999999999995, |
| "grad_norm": 0.029351714998483658, |
| "learning_rate": 2.98558587804993e-05, |
| "loss": 0.0009, |
| "step": 247 |
| }, |
| { |
| "epoch": 4.96, |
| "grad_norm": 0.046229105442762375, |
| "learning_rate": 2.9684532864643122e-05, |
| "loss": 0.0009, |
| "step": 248 |
| }, |
| { |
| "epoch": 4.98, |
| "grad_norm": 0.4148816764354706, |
| "learning_rate": 2.9512978631264006e-05, |
| "loss": 0.0009, |
| "step": 249 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.12848469614982605, |
| "learning_rate": 2.9341204441673266e-05, |
| "loss": 0.001, |
| "step": 250 |
| }, |
| { |
| "epoch": 5.02, |
| "grad_norm": 0.01425765361636877, |
| "learning_rate": 2.916921866790256e-05, |
| "loss": 0.0008, |
| "step": 251 |
| }, |
| { |
| "epoch": 5.04, |
| "grad_norm": 0.020687583833932877, |
| "learning_rate": 2.8997029692295874e-05, |
| "loss": 0.0008, |
| "step": 252 |
| }, |
| { |
| "epoch": 5.06, |
| "grad_norm": 0.016962770372629166, |
| "learning_rate": 2.8824645907100954e-05, |
| "loss": 0.0009, |
| "step": 253 |
| }, |
| { |
| "epoch": 5.08, |
| "grad_norm": 0.016928350552916527, |
| "learning_rate": 2.8652075714060295e-05, |
| "loss": 0.0008, |
| "step": 254 |
| }, |
| { |
| "epoch": 5.1, |
| "grad_norm": 0.035252753645181656, |
| "learning_rate": 2.8479327524001636e-05, |
| "loss": 0.0009, |
| "step": 255 |
| }, |
| { |
| "epoch": 5.12, |
| "grad_norm": 0.015413952991366386, |
| "learning_rate": 2.8306409756428064e-05, |
| "loss": 0.0008, |
| "step": 256 |
| }, |
| { |
| "epoch": 5.14, |
| "grad_norm": 0.023872479796409607, |
| "learning_rate": 2.8133330839107608e-05, |
| "loss": 0.0009, |
| "step": 257 |
| }, |
| { |
| "epoch": 5.16, |
| "grad_norm": 0.013683849945664406, |
| "learning_rate": 2.7960099207662532e-05, |
| "loss": 0.0008, |
| "step": 258 |
| }, |
| { |
| "epoch": 5.18, |
| "grad_norm": 0.021965356543660164, |
| "learning_rate": 2.7786723305158136e-05, |
| "loss": 0.0009, |
| "step": 259 |
| }, |
| { |
| "epoch": 5.2, |
| "grad_norm": 0.018004387617111206, |
| "learning_rate": 2.761321158169134e-05, |
| "loss": 0.0008, |
| "step": 260 |
| }, |
| { |
| "epoch": 5.22, |
| "grad_norm": 0.10878186672925949, |
| "learning_rate": 2.7439572493978736e-05, |
| "loss": 0.0009, |
| "step": 261 |
| }, |
| { |
| "epoch": 5.24, |
| "grad_norm": 0.016990287229418755, |
| "learning_rate": 2.726581450494451e-05, |
| "loss": 0.0009, |
| "step": 262 |
| }, |
| { |
| "epoch": 5.26, |
| "grad_norm": 0.019985131919384003, |
| "learning_rate": 2.7091946083307896e-05, |
| "loss": 0.001, |
| "step": 263 |
| }, |
| { |
| "epoch": 5.28, |
| "grad_norm": 0.019697532057762146, |
| "learning_rate": 2.6917975703170466e-05, |
| "loss": 0.001, |
| "step": 264 |
| }, |
| { |
| "epoch": 5.3, |
| "grad_norm": 0.02688547596335411, |
| "learning_rate": 2.674391184360313e-05, |
| "loss": 0.001, |
| "step": 265 |
| }, |
| { |
| "epoch": 5.32, |
| "grad_norm": 0.019830502569675446, |
| "learning_rate": 2.656976298823284e-05, |
| "loss": 0.001, |
| "step": 266 |
| }, |
| { |
| "epoch": 5.34, |
| "grad_norm": 0.00932388100773096, |
| "learning_rate": 2.6395537624829096e-05, |
| "loss": 0.0009, |
| "step": 267 |
| }, |
| { |
| "epoch": 5.36, |
| "grad_norm": 0.022172892466187477, |
| "learning_rate": 2.6221244244890336e-05, |
| "loss": 0.0011, |
| "step": 268 |
| }, |
| { |
| "epoch": 5.38, |
| "grad_norm": 0.013382075354456902, |
| "learning_rate": 2.604689134322999e-05, |
| "loss": 0.0009, |
| "step": 269 |
| }, |
| { |
| "epoch": 5.4, |
| "grad_norm": 0.011492418125271797, |
| "learning_rate": 2.587248741756253e-05, |
| "loss": 0.0009, |
| "step": 270 |
| }, |
| { |
| "epoch": 5.42, |
| "grad_norm": 0.014342604205012321, |
| "learning_rate": 2.5698040968089225e-05, |
| "loss": 0.001, |
| "step": 271 |
| }, |
| { |
| "epoch": 5.44, |
| "grad_norm": 0.014334768988192081, |
| "learning_rate": 2.5523560497083926e-05, |
| "loss": 0.0009, |
| "step": 272 |
| }, |
| { |
| "epoch": 5.46, |
| "grad_norm": 0.00868277158588171, |
| "learning_rate": 2.5349054508478637e-05, |
| "loss": 0.0009, |
| "step": 273 |
| }, |
| { |
| "epoch": 5.48, |
| "grad_norm": 0.015255315229296684, |
| "learning_rate": 2.517453150744904e-05, |
| "loss": 0.0009, |
| "step": 274 |
| }, |
| { |
| "epoch": 5.5, |
| "grad_norm": 0.014761993661522865, |
| "learning_rate": 2.5e-05, |
| "loss": 0.0009, |
| "step": 275 |
| }, |
| { |
| "epoch": 5.52, |
| "grad_norm": 0.01535094901919365, |
| "learning_rate": 2.4825468492550964e-05, |
| "loss": 0.0009, |
| "step": 276 |
| }, |
| { |
| "epoch": 5.54, |
| "grad_norm": 0.018661124631762505, |
| "learning_rate": 2.4650945491521372e-05, |
| "loss": 0.001, |
| "step": 277 |
| }, |
| { |
| "epoch": 5.5600000000000005, |
| "grad_norm": 0.015340641140937805, |
| "learning_rate": 2.447643950291608e-05, |
| "loss": 0.001, |
| "step": 278 |
| }, |
| { |
| "epoch": 5.58, |
| "grad_norm": 0.011068003252148628, |
| "learning_rate": 2.4301959031910784e-05, |
| "loss": 0.001, |
| "step": 279 |
| }, |
| { |
| "epoch": 5.6, |
| "grad_norm": 0.011561702005565166, |
| "learning_rate": 2.4127512582437485e-05, |
| "loss": 0.001, |
| "step": 280 |
| }, |
| { |
| "epoch": 5.62, |
| "grad_norm": 0.0134280975908041, |
| "learning_rate": 2.3953108656770016e-05, |
| "loss": 0.001, |
| "step": 281 |
| }, |
| { |
| "epoch": 5.64, |
| "grad_norm": 0.010531393811106682, |
| "learning_rate": 2.377875575510967e-05, |
| "loss": 0.001, |
| "step": 282 |
| }, |
| { |
| "epoch": 5.66, |
| "grad_norm": 0.0099195446819067, |
| "learning_rate": 2.3604462375170906e-05, |
| "loss": 0.0009, |
| "step": 283 |
| }, |
| { |
| "epoch": 5.68, |
| "grad_norm": 0.008749845437705517, |
| "learning_rate": 2.3430237011767167e-05, |
| "loss": 0.0009, |
| "step": 284 |
| }, |
| { |
| "epoch": 5.7, |
| "grad_norm": 0.00893120002001524, |
| "learning_rate": 2.3256088156396868e-05, |
| "loss": 0.0009, |
| "step": 285 |
| }, |
| { |
| "epoch": 5.72, |
| "grad_norm": 0.010007224045693874, |
| "learning_rate": 2.3082024296829536e-05, |
| "loss": 0.001, |
| "step": 286 |
| }, |
| { |
| "epoch": 5.74, |
| "grad_norm": 0.008720742538571358, |
| "learning_rate": 2.2908053916692117e-05, |
| "loss": 0.0009, |
| "step": 287 |
| }, |
| { |
| "epoch": 5.76, |
| "grad_norm": 0.006999673787504435, |
| "learning_rate": 2.2734185495055503e-05, |
| "loss": 0.0009, |
| "step": 288 |
| }, |
| { |
| "epoch": 5.78, |
| "grad_norm": 0.016226548701524734, |
| "learning_rate": 2.2560427506021266e-05, |
| "loss": 0.0009, |
| "step": 289 |
| }, |
| { |
| "epoch": 5.8, |
| "grad_norm": 0.012789979577064514, |
| "learning_rate": 2.238678841830867e-05, |
| "loss": 0.001, |
| "step": 290 |
| }, |
| { |
| "epoch": 5.82, |
| "grad_norm": 0.012711182236671448, |
| "learning_rate": 2.2213276694841866e-05, |
| "loss": 0.001, |
| "step": 291 |
| }, |
| { |
| "epoch": 5.84, |
| "grad_norm": 0.011736830696463585, |
| "learning_rate": 2.2039900792337474e-05, |
| "loss": 0.0009, |
| "step": 292 |
| }, |
| { |
| "epoch": 5.86, |
| "grad_norm": 0.0094444639980793, |
| "learning_rate": 2.186666916089239e-05, |
| "loss": 0.0009, |
| "step": 293 |
| }, |
| { |
| "epoch": 5.88, |
| "grad_norm": 0.014789476990699768, |
| "learning_rate": 2.1693590243571938e-05, |
| "loss": 0.0009, |
| "step": 294 |
| }, |
| { |
| "epoch": 5.9, |
| "grad_norm": 0.014187824912369251, |
| "learning_rate": 2.1520672475998373e-05, |
| "loss": 0.001, |
| "step": 295 |
| }, |
| { |
| "epoch": 5.92, |
| "grad_norm": 0.018324721604585648, |
| "learning_rate": 2.1347924285939714e-05, |
| "loss": 0.001, |
| "step": 296 |
| }, |
| { |
| "epoch": 5.9399999999999995, |
| "grad_norm": 0.012350255623459816, |
| "learning_rate": 2.117535409289905e-05, |
| "loss": 0.0009, |
| "step": 297 |
| }, |
| { |
| "epoch": 5.96, |
| "grad_norm": 0.011847893707454205, |
| "learning_rate": 2.1002970307704132e-05, |
| "loss": 0.001, |
| "step": 298 |
| }, |
| { |
| "epoch": 5.98, |
| "grad_norm": 0.011209225282073021, |
| "learning_rate": 2.0830781332097446e-05, |
| "loss": 0.0009, |
| "step": 299 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 0.009176170453429222, |
| "learning_rate": 2.0658795558326743e-05, |
| "loss": 0.0009, |
| "step": 300 |
| }, |
| { |
| "epoch": 6.02, |
| "grad_norm": 0.013149021193385124, |
| "learning_rate": 2.0487021368736003e-05, |
| "loss": 0.0008, |
| "step": 301 |
| }, |
| { |
| "epoch": 6.04, |
| "grad_norm": 0.020946791395545006, |
| "learning_rate": 2.031546713535688e-05, |
| "loss": 0.0009, |
| "step": 302 |
| }, |
| { |
| "epoch": 6.06, |
| "grad_norm": 0.05294759199023247, |
| "learning_rate": 2.0144141219500705e-05, |
| "loss": 0.0009, |
| "step": 303 |
| }, |
| { |
| "epoch": 6.08, |
| "grad_norm": 0.014098895713686943, |
| "learning_rate": 1.9973051971350888e-05, |
| "loss": 0.0009, |
| "step": 304 |
| }, |
| { |
| "epoch": 6.1, |
| "grad_norm": 0.01258071605116129, |
| "learning_rate": 1.980220772955602e-05, |
| "loss": 0.0009, |
| "step": 305 |
| }, |
| { |
| "epoch": 6.12, |
| "grad_norm": 0.01646529696881771, |
| "learning_rate": 1.963161682082342e-05, |
| "loss": 0.0009, |
| "step": 306 |
| }, |
| { |
| "epoch": 6.14, |
| "grad_norm": 0.01562797650694847, |
| "learning_rate": 1.946128755951332e-05, |
| "loss": 0.001, |
| "step": 307 |
| }, |
| { |
| "epoch": 6.16, |
| "grad_norm": 0.02843649871647358, |
| "learning_rate": 1.9291228247233605e-05, |
| "loss": 0.0008, |
| "step": 308 |
| }, |
| { |
| "epoch": 6.18, |
| "grad_norm": 0.015122253447771072, |
| "learning_rate": 1.912144717243525e-05, |
| "loss": 0.0009, |
| "step": 309 |
| }, |
| { |
| "epoch": 6.2, |
| "grad_norm": 0.024031292647123337, |
| "learning_rate": 1.895195261000831e-05, |
| "loss": 0.0008, |
| "step": 310 |
| }, |
| { |
| "epoch": 6.22, |
| "grad_norm": 0.017758721485733986, |
| "learning_rate": 1.8782752820878634e-05, |
| "loss": 0.001, |
| "step": 311 |
| }, |
| { |
| "epoch": 6.24, |
| "grad_norm": 0.018115799874067307, |
| "learning_rate": 1.8613856051605243e-05, |
| "loss": 0.0009, |
| "step": 312 |
| }, |
| { |
| "epoch": 6.26, |
| "grad_norm": 0.013583043590188026, |
| "learning_rate": 1.8445270533978388e-05, |
| "loss": 0.001, |
| "step": 313 |
| }, |
| { |
| "epoch": 6.28, |
| "grad_norm": 0.01605222374200821, |
| "learning_rate": 1.827700448461836e-05, |
| "loss": 0.0009, |
| "step": 314 |
| }, |
| { |
| "epoch": 6.3, |
| "grad_norm": 0.012071061879396439, |
| "learning_rate": 1.8109066104575023e-05, |
| "loss": 0.0009, |
| "step": 315 |
| }, |
| { |
| "epoch": 6.32, |
| "grad_norm": 0.02086683176457882, |
| "learning_rate": 1.7941463578928086e-05, |
| "loss": 0.0008, |
| "step": 316 |
| }, |
| { |
| "epoch": 6.34, |
| "grad_norm": 0.015499988570809364, |
| "learning_rate": 1.7774205076388206e-05, |
| "loss": 0.001, |
| "step": 317 |
| }, |
| { |
| "epoch": 6.36, |
| "grad_norm": 0.033231064677238464, |
| "learning_rate": 1.7607298748898842e-05, |
| "loss": 0.001, |
| "step": 318 |
| }, |
| { |
| "epoch": 6.38, |
| "grad_norm": 0.04200902208685875, |
| "learning_rate": 1.744075273123889e-05, |
| "loss": 0.001, |
| "step": 319 |
| }, |
| { |
| "epoch": 6.4, |
| "grad_norm": 0.016907304525375366, |
| "learning_rate": 1.7274575140626318e-05, |
| "loss": 0.0009, |
| "step": 320 |
| }, |
| { |
| "epoch": 6.42, |
| "grad_norm": 0.012497249990701675, |
| "learning_rate": 1.7108774076322443e-05, |
| "loss": 0.0008, |
| "step": 321 |
| }, |
| { |
| "epoch": 6.44, |
| "grad_norm": 0.01482861116528511, |
| "learning_rate": 1.6943357619237226e-05, |
| "loss": 0.0009, |
| "step": 322 |
| }, |
| { |
| "epoch": 6.46, |
| "grad_norm": 0.010810253210365772, |
| "learning_rate": 1.677833383153542e-05, |
| "loss": 0.0009, |
| "step": 323 |
| }, |
| { |
| "epoch": 6.48, |
| "grad_norm": 0.008798140101134777, |
| "learning_rate": 1.6613710756243626e-05, |
| "loss": 0.0008, |
| "step": 324 |
| }, |
| { |
| "epoch": 6.5, |
| "grad_norm": 0.011670750565826893, |
| "learning_rate": 1.6449496416858284e-05, |
| "loss": 0.0009, |
| "step": 325 |
| }, |
| { |
| "epoch": 6.52, |
| "grad_norm": 0.013968761079013348, |
| "learning_rate": 1.6285698816954624e-05, |
| "loss": 0.0009, |
| "step": 326 |
| }, |
| { |
| "epoch": 6.54, |
| "grad_norm": 0.014013497158885002, |
| "learning_rate": 1.612232593979658e-05, |
| "loss": 0.0009, |
| "step": 327 |
| }, |
| { |
| "epoch": 6.5600000000000005, |
| "grad_norm": 0.01848709024488926, |
| "learning_rate": 1.5959385747947698e-05, |
| "loss": 0.0008, |
| "step": 328 |
| }, |
| { |
| "epoch": 6.58, |
| "grad_norm": 0.02498721145093441, |
| "learning_rate": 1.5796886182883053e-05, |
| "loss": 0.001, |
| "step": 329 |
| }, |
| { |
| "epoch": 6.6, |
| "grad_norm": 0.01326808612793684, |
| "learning_rate": 1.56348351646022e-05, |
| "loss": 0.001, |
| "step": 330 |
| }, |
| { |
| "epoch": 6.62, |
| "grad_norm": 0.014568154700100422, |
| "learning_rate": 1.547324059124315e-05, |
| "loss": 0.0009, |
| "step": 331 |
| }, |
| { |
| "epoch": 6.64, |
| "grad_norm": 0.012086485512554646, |
| "learning_rate": 1.5312110338697426e-05, |
| "loss": 0.001, |
| "step": 332 |
| }, |
| { |
| "epoch": 6.66, |
| "grad_norm": 0.010840130038559437, |
| "learning_rate": 1.5151452260226224e-05, |
| "loss": 0.0008, |
| "step": 333 |
| }, |
| { |
| "epoch": 6.68, |
| "grad_norm": 0.012208978645503521, |
| "learning_rate": 1.4991274186077632e-05, |
| "loss": 0.001, |
| "step": 334 |
| }, |
| { |
| "epoch": 6.7, |
| "grad_norm": 0.01624949462711811, |
| "learning_rate": 1.4831583923104999e-05, |
| "loss": 0.0009, |
| "step": 335 |
| }, |
| { |
| "epoch": 6.72, |
| "grad_norm": 0.01066320575773716, |
| "learning_rate": 1.467238925438646e-05, |
| "loss": 0.0008, |
| "step": 336 |
| }, |
| { |
| "epoch": 6.74, |
| "grad_norm": 0.015944579616189003, |
| "learning_rate": 1.4513697938845572e-05, |
| "loss": 0.001, |
| "step": 337 |
| }, |
| { |
| "epoch": 6.76, |
| "grad_norm": 0.011701629497110844, |
| "learning_rate": 1.4355517710873184e-05, |
| "loss": 0.0008, |
| "step": 338 |
| }, |
| { |
| "epoch": 6.78, |
| "grad_norm": 0.011669070459902287, |
| "learning_rate": 1.4197856279950438e-05, |
| "loss": 0.0009, |
| "step": 339 |
| }, |
| { |
| "epoch": 6.8, |
| "grad_norm": 0.08641933649778366, |
| "learning_rate": 1.4040721330273062e-05, |
| "loss": 0.0009, |
| "step": 340 |
| }, |
| { |
| "epoch": 6.82, |
| "grad_norm": 0.028719276189804077, |
| "learning_rate": 1.388412052037682e-05, |
| "loss": 0.0009, |
| "step": 341 |
| }, |
| { |
| "epoch": 6.84, |
| "grad_norm": 0.011268166825175285, |
| "learning_rate": 1.3728061482764238e-05, |
| "loss": 0.0009, |
| "step": 342 |
| }, |
| { |
| "epoch": 6.86, |
| "grad_norm": 0.013131314888596535, |
| "learning_rate": 1.3572551823532654e-05, |
| "loss": 0.0008, |
| "step": 343 |
| }, |
| { |
| "epoch": 6.88, |
| "grad_norm": 0.010851713828742504, |
| "learning_rate": 1.3417599122003464e-05, |
| "loss": 0.0009, |
| "step": 344 |
| }, |
| { |
| "epoch": 6.9, |
| "grad_norm": 0.013467922806739807, |
| "learning_rate": 1.3263210930352737e-05, |
| "loss": 0.0008, |
| "step": 345 |
| }, |
| { |
| "epoch": 6.92, |
| "grad_norm": 0.013433183543384075, |
| "learning_rate": 1.3109394773243117e-05, |
| "loss": 0.0009, |
| "step": 346 |
| }, |
| { |
| "epoch": 6.9399999999999995, |
| "grad_norm": 0.010768929496407509, |
| "learning_rate": 1.2956158147457115e-05, |
| "loss": 0.0008, |
| "step": 347 |
| }, |
| { |
| "epoch": 6.96, |
| "grad_norm": 0.011435325257480145, |
| "learning_rate": 1.280350852153168e-05, |
| "loss": 0.0008, |
| "step": 348 |
| }, |
| { |
| "epoch": 6.98, |
| "grad_norm": 0.012479741126298904, |
| "learning_rate": 1.2651453335394231e-05, |
| "loss": 0.0009, |
| "step": 349 |
| }, |
| { |
| "epoch": 7.0, |
| "grad_norm": 0.013233255594968796, |
| "learning_rate": 1.2500000000000006e-05, |
| "loss": 0.0009, |
| "step": 350 |
| }, |
| { |
| "epoch": 7.02, |
| "grad_norm": 0.012486303225159645, |
| "learning_rate": 1.234915589697091e-05, |
| "loss": 0.001, |
| "step": 351 |
| }, |
| { |
| "epoch": 7.04, |
| "grad_norm": 0.011426866985857487, |
| "learning_rate": 1.2198928378235716e-05, |
| "loss": 0.0008, |
| "step": 352 |
| }, |
| { |
| "epoch": 7.06, |
| "grad_norm": 0.009702113457024097, |
| "learning_rate": 1.2049324765671749e-05, |
| "loss": 0.0008, |
| "step": 353 |
| }, |
| { |
| "epoch": 7.08, |
| "grad_norm": 0.014162976294755936, |
| "learning_rate": 1.1900352350748026e-05, |
| "loss": 0.0009, |
| "step": 354 |
| }, |
| { |
| "epoch": 7.1, |
| "grad_norm": 0.028280340135097504, |
| "learning_rate": 1.175201839416988e-05, |
| "loss": 0.0008, |
| "step": 355 |
| }, |
| { |
| "epoch": 7.12, |
| "grad_norm": 0.012857620604336262, |
| "learning_rate": 1.1604330125525079e-05, |
| "loss": 0.0009, |
| "step": 356 |
| }, |
| { |
| "epoch": 7.14, |
| "grad_norm": 0.011418178677558899, |
| "learning_rate": 1.1457294742931507e-05, |
| "loss": 0.0007, |
| "step": 357 |
| }, |
| { |
| "epoch": 7.16, |
| "grad_norm": 0.02243344485759735, |
| "learning_rate": 1.1310919412686247e-05, |
| "loss": 0.0008, |
| "step": 358 |
| }, |
| { |
| "epoch": 7.18, |
| "grad_norm": 0.009756579995155334, |
| "learning_rate": 1.11652112689164e-05, |
| "loss": 0.0007, |
| "step": 359 |
| }, |
| { |
| "epoch": 7.2, |
| "grad_norm": 0.033040065318346024, |
| "learning_rate": 1.1020177413231334e-05, |
| "loss": 0.0009, |
| "step": 360 |
| }, |
| { |
| "epoch": 7.22, |
| "grad_norm": 0.011751036159694195, |
| "learning_rate": 1.0875824914376553e-05, |
| "loss": 0.0008, |
| "step": 361 |
| }, |
| { |
| "epoch": 7.24, |
| "grad_norm": 0.02029712125658989, |
| "learning_rate": 1.0732160807889211e-05, |
| "loss": 0.0009, |
| "step": 362 |
| }, |
| { |
| "epoch": 7.26, |
| "grad_norm": 0.012680457904934883, |
| "learning_rate": 1.058919209575517e-05, |
| "loss": 0.0007, |
| "step": 363 |
| }, |
| { |
| "epoch": 7.28, |
| "grad_norm": 0.01278097927570343, |
| "learning_rate": 1.0446925746067768e-05, |
| "loss": 0.0007, |
| "step": 364 |
| }, |
| { |
| "epoch": 7.3, |
| "grad_norm": 0.017604360356926918, |
| "learning_rate": 1.0305368692688174e-05, |
| "loss": 0.0008, |
| "step": 365 |
| }, |
| { |
| "epoch": 7.32, |
| "grad_norm": 0.012253907509148121, |
| "learning_rate": 1.0164527834907467e-05, |
| "loss": 0.0007, |
| "step": 366 |
| }, |
| { |
| "epoch": 7.34, |
| "grad_norm": 0.01415831595659256, |
| "learning_rate": 1.0024410037110357e-05, |
| "loss": 0.0007, |
| "step": 367 |
| }, |
| { |
| "epoch": 7.36, |
| "grad_norm": 0.01281712669879198, |
| "learning_rate": 9.88502212844063e-06, |
| "loss": 0.0008, |
| "step": 368 |
| }, |
| { |
| "epoch": 7.38, |
| "grad_norm": 0.01478048600256443, |
| "learning_rate": 9.746370902468311e-06, |
| "loss": 0.0008, |
| "step": 369 |
| }, |
| { |
| "epoch": 7.4, |
| "grad_norm": 0.05853793025016785, |
| "learning_rate": 9.608463116858542e-06, |
| "loss": 0.0009, |
| "step": 370 |
| }, |
| { |
| "epoch": 7.42, |
| "grad_norm": 0.011016006581485271, |
| "learning_rate": 9.471305493042243e-06, |
| "loss": 0.0008, |
| "step": 371 |
| }, |
| { |
| "epoch": 7.44, |
| "grad_norm": 0.01250209379941225, |
| "learning_rate": 9.334904715888495e-06, |
| "loss": 0.0007, |
| "step": 372 |
| }, |
| { |
| "epoch": 7.46, |
| "grad_norm": 0.01570058800280094, |
| "learning_rate": 9.199267433378727e-06, |
| "loss": 0.0008, |
| "step": 373 |
| }, |
| { |
| "epoch": 7.48, |
| "grad_norm": 0.021531647071242332, |
| "learning_rate": 9.064400256282757e-06, |
| "loss": 0.001, |
| "step": 374 |
| }, |
| { |
| "epoch": 7.5, |
| "grad_norm": 0.021758703514933586, |
| "learning_rate": 8.930309757836517e-06, |
| "loss": 0.0008, |
| "step": 375 |
| }, |
| { |
| "epoch": 7.52, |
| "grad_norm": 0.01226816326379776, |
| "learning_rate": 8.797002473421728e-06, |
| "loss": 0.0007, |
| "step": 376 |
| }, |
| { |
| "epoch": 7.54, |
| "grad_norm": 0.024715250357985497, |
| "learning_rate": 8.664484900247363e-06, |
| "loss": 0.0008, |
| "step": 377 |
| }, |
| { |
| "epoch": 7.5600000000000005, |
| "grad_norm": 0.01861533895134926, |
| "learning_rate": 8.532763497032987e-06, |
| "loss": 0.0007, |
| "step": 378 |
| }, |
| { |
| "epoch": 7.58, |
| "grad_norm": 0.019747568294405937, |
| "learning_rate": 8.40184468369396e-06, |
| "loss": 0.0008, |
| "step": 379 |
| }, |
| { |
| "epoch": 7.6, |
| "grad_norm": 0.01395918894559145, |
| "learning_rate": 8.271734841028553e-06, |
| "loss": 0.0007, |
| "step": 380 |
| }, |
| { |
| "epoch": 7.62, |
| "grad_norm": 0.011769567616283894, |
| "learning_rate": 8.142440310406924e-06, |
| "loss": 0.0008, |
| "step": 381 |
| }, |
| { |
| "epoch": 7.64, |
| "grad_norm": 0.017392277717590332, |
| "learning_rate": 8.013967393462094e-06, |
| "loss": 0.0008, |
| "step": 382 |
| }, |
| { |
| "epoch": 7.66, |
| "grad_norm": 0.016862329095602036, |
| "learning_rate": 7.886322351782783e-06, |
| "loss": 0.0008, |
| "step": 383 |
| }, |
| { |
| "epoch": 7.68, |
| "grad_norm": 0.011566593311727047, |
| "learning_rate": 7.759511406608255e-06, |
| "loss": 0.0008, |
| "step": 384 |
| }, |
| { |
| "epoch": 7.7, |
| "grad_norm": 0.014474247582256794, |
| "learning_rate": 7.633540738525066e-06, |
| "loss": 0.0009, |
| "step": 385 |
| }, |
| { |
| "epoch": 7.72, |
| "grad_norm": 0.031276676803827286, |
| "learning_rate": 7.508416487165862e-06, |
| "loss": 0.0008, |
| "step": 386 |
| }, |
| { |
| "epoch": 7.74, |
| "grad_norm": 0.011668872088193893, |
| "learning_rate": 7.384144750910133e-06, |
| "loss": 0.0008, |
| "step": 387 |
| }, |
| { |
| "epoch": 7.76, |
| "grad_norm": 0.014757595956325531, |
| "learning_rate": 7.260731586586983e-06, |
| "loss": 0.0008, |
| "step": 388 |
| }, |
| { |
| "epoch": 7.78, |
| "grad_norm": 0.020262010395526886, |
| "learning_rate": 7.138183009179922e-06, |
| "loss": 0.0008, |
| "step": 389 |
| }, |
| { |
| "epoch": 7.8, |
| "grad_norm": 0.012966041453182697, |
| "learning_rate": 7.016504991533726e-06, |
| "loss": 0.0009, |
| "step": 390 |
| }, |
| { |
| "epoch": 7.82, |
| "grad_norm": 0.02517668902873993, |
| "learning_rate": 6.895703464063319e-06, |
| "loss": 0.0009, |
| "step": 391 |
| }, |
| { |
| "epoch": 7.84, |
| "grad_norm": 0.008584852330386639, |
| "learning_rate": 6.775784314464717e-06, |
| "loss": 0.0007, |
| "step": 392 |
| }, |
| { |
| "epoch": 7.86, |
| "grad_norm": 0.01465829461812973, |
| "learning_rate": 6.656753387428089e-06, |
| "loss": 0.0007, |
| "step": 393 |
| }, |
| { |
| "epoch": 7.88, |
| "grad_norm": 0.011138123460114002, |
| "learning_rate": 6.538616484352902e-06, |
| "loss": 0.0008, |
| "step": 394 |
| }, |
| { |
| "epoch": 7.9, |
| "grad_norm": 0.022989438846707344, |
| "learning_rate": 6.421379363065142e-06, |
| "loss": 0.0009, |
| "step": 395 |
| }, |
| { |
| "epoch": 7.92, |
| "grad_norm": 0.013544759713113308, |
| "learning_rate": 6.305047737536707e-06, |
| "loss": 0.0009, |
| "step": 396 |
| }, |
| { |
| "epoch": 7.9399999999999995, |
| "grad_norm": 0.016775785014033318, |
| "learning_rate": 6.189627277606894e-06, |
| "loss": 0.0008, |
| "step": 397 |
| }, |
| { |
| "epoch": 7.96, |
| "grad_norm": 0.012762874364852905, |
| "learning_rate": 6.075123608706093e-06, |
| "loss": 0.0008, |
| "step": 398 |
| }, |
| { |
| "epoch": 7.98, |
| "grad_norm": 0.01835818588733673, |
| "learning_rate": 5.961542311581586e-06, |
| "loss": 0.0008, |
| "step": 399 |
| }, |
| { |
| "epoch": 8.0, |
| "grad_norm": 0.024637369439005852, |
| "learning_rate": 5.848888922025553e-06, |
| "loss": 0.0007, |
| "step": 400 |
| }, |
| { |
| "epoch": 8.02, |
| "grad_norm": 0.016956869512796402, |
| "learning_rate": 5.737168930605272e-06, |
| "loss": 0.0007, |
| "step": 401 |
| }, |
| { |
| "epoch": 8.04, |
| "grad_norm": 0.012730157002806664, |
| "learning_rate": 5.626387782395512e-06, |
| "loss": 0.0006, |
| "step": 402 |
| }, |
| { |
| "epoch": 8.06, |
| "grad_norm": 0.01208969485014677, |
| "learning_rate": 5.5165508767131415e-06, |
| "loss": 0.0007, |
| "step": 403 |
| }, |
| { |
| "epoch": 8.08, |
| "grad_norm": 0.01699792966246605, |
| "learning_rate": 5.4076635668540075e-06, |
| "loss": 0.0006, |
| "step": 404 |
| }, |
| { |
| "epoch": 8.1, |
| "grad_norm": 0.014854060485959053, |
| "learning_rate": 5.299731159831953e-06, |
| "loss": 0.0007, |
| "step": 405 |
| }, |
| { |
| "epoch": 8.12, |
| "grad_norm": 0.012892371043562889, |
| "learning_rate": 5.192758916120236e-06, |
| "loss": 0.0006, |
| "step": 406 |
| }, |
| { |
| "epoch": 8.14, |
| "grad_norm": 0.015144885517656803, |
| "learning_rate": 5.086752049395094e-06, |
| "loss": 0.0007, |
| "step": 407 |
| }, |
| { |
| "epoch": 8.16, |
| "grad_norm": 0.014186014421284199, |
| "learning_rate": 4.981715726281666e-06, |
| "loss": 0.0008, |
| "step": 408 |
| }, |
| { |
| "epoch": 8.18, |
| "grad_norm": 0.015514220111072063, |
| "learning_rate": 4.877655066102149e-06, |
| "loss": 0.0007, |
| "step": 409 |
| }, |
| { |
| "epoch": 8.2, |
| "grad_norm": 0.015736915171146393, |
| "learning_rate": 4.7745751406263165e-06, |
| "loss": 0.0006, |
| "step": 410 |
| }, |
| { |
| "epoch": 8.22, |
| "grad_norm": 0.012078430503606796, |
| "learning_rate": 4.672480973824311e-06, |
| "loss": 0.0008, |
| "step": 411 |
| }, |
| { |
| "epoch": 8.24, |
| "grad_norm": 0.02000226080417633, |
| "learning_rate": 4.571377541621788e-06, |
| "loss": 0.0007, |
| "step": 412 |
| }, |
| { |
| "epoch": 8.26, |
| "grad_norm": 0.011416291818022728, |
| "learning_rate": 4.4712697716574e-06, |
| "loss": 0.0006, |
| "step": 413 |
| }, |
| { |
| "epoch": 8.28, |
| "grad_norm": 0.022556310519576073, |
| "learning_rate": 4.372162543042624e-06, |
| "loss": 0.0008, |
| "step": 414 |
| }, |
| { |
| "epoch": 8.3, |
| "grad_norm": 0.02372623048722744, |
| "learning_rate": 4.274060686123959e-06, |
| "loss": 0.0007, |
| "step": 415 |
| }, |
| { |
| "epoch": 8.32, |
| "grad_norm": 0.02283402346074581, |
| "learning_rate": 4.176968982247514e-06, |
| "loss": 0.0007, |
| "step": 416 |
| }, |
| { |
| "epoch": 8.34, |
| "grad_norm": 0.020453330129384995, |
| "learning_rate": 4.08089216352596e-06, |
| "loss": 0.0006, |
| "step": 417 |
| }, |
| { |
| "epoch": 8.36, |
| "grad_norm": 0.014580060727894306, |
| "learning_rate": 3.985834912607894e-06, |
| "loss": 0.0007, |
| "step": 418 |
| }, |
| { |
| "epoch": 8.38, |
| "grad_norm": 0.011051076464354992, |
| "learning_rate": 3.891801862449629e-06, |
| "loss": 0.0007, |
| "step": 419 |
| }, |
| { |
| "epoch": 8.4, |
| "grad_norm": 0.03123440593481064, |
| "learning_rate": 3.798797596089351e-06, |
| "loss": 0.0007, |
| "step": 420 |
| }, |
| { |
| "epoch": 8.42, |
| "grad_norm": 0.008824478834867477, |
| "learning_rate": 3.7068266464238084e-06, |
| "loss": 0.0005, |
| "step": 421 |
| }, |
| { |
| "epoch": 8.44, |
| "grad_norm": 0.01253305934369564, |
| "learning_rate": 3.6158934959873353e-06, |
| "loss": 0.0006, |
| "step": 422 |
| }, |
| { |
| "epoch": 8.46, |
| "grad_norm": 0.011405512690544128, |
| "learning_rate": 3.5260025767333893e-06, |
| "loss": 0.0007, |
| "step": 423 |
| }, |
| { |
| "epoch": 8.48, |
| "grad_norm": 0.01283338014036417, |
| "learning_rate": 3.4371582698185633e-06, |
| "loss": 0.0007, |
| "step": 424 |
| }, |
| { |
| "epoch": 8.5, |
| "grad_norm": 0.012804213911294937, |
| "learning_rate": 3.3493649053890326e-06, |
| "loss": 0.0007, |
| "step": 425 |
| }, |
| { |
| "epoch": 8.52, |
| "grad_norm": 0.012545102275907993, |
| "learning_rate": 3.262626762369525e-06, |
| "loss": 0.0007, |
| "step": 426 |
| }, |
| { |
| "epoch": 8.54, |
| "grad_norm": 0.012686868198215961, |
| "learning_rate": 3.176948068254762e-06, |
| "loss": 0.0007, |
| "step": 427 |
| }, |
| { |
| "epoch": 8.56, |
| "grad_norm": 0.018044594675302505, |
| "learning_rate": 3.092332998903416e-06, |
| "loss": 0.0007, |
| "step": 428 |
| }, |
| { |
| "epoch": 8.58, |
| "grad_norm": 0.017359774559736252, |
| "learning_rate": 3.0087856783345914e-06, |
| "loss": 0.0007, |
| "step": 429 |
| }, |
| { |
| "epoch": 8.6, |
| "grad_norm": 0.019643310457468033, |
| "learning_rate": 2.9263101785268254e-06, |
| "loss": 0.0007, |
| "step": 430 |
| }, |
| { |
| "epoch": 8.62, |
| "grad_norm": 0.015051987022161484, |
| "learning_rate": 2.8449105192196316e-06, |
| "loss": 0.0007, |
| "step": 431 |
| }, |
| { |
| "epoch": 8.64, |
| "grad_norm": 0.014268382452428341, |
| "learning_rate": 2.764590667717562e-06, |
| "loss": 0.0007, |
| "step": 432 |
| }, |
| { |
| "epoch": 8.66, |
| "grad_norm": 0.013278437778353691, |
| "learning_rate": 2.6853545386968606e-06, |
| "loss": 0.0008, |
| "step": 433 |
| }, |
| { |
| "epoch": 8.68, |
| "grad_norm": 0.03189530596137047, |
| "learning_rate": 2.6072059940146775e-06, |
| "loss": 0.0007, |
| "step": 434 |
| }, |
| { |
| "epoch": 8.7, |
| "grad_norm": 0.08232607692480087, |
| "learning_rate": 2.5301488425208296e-06, |
| "loss": 0.0007, |
| "step": 435 |
| }, |
| { |
| "epoch": 8.72, |
| "grad_norm": 0.01643546111881733, |
| "learning_rate": 2.454186839872158e-06, |
| "loss": 0.0008, |
| "step": 436 |
| }, |
| { |
| "epoch": 8.74, |
| "grad_norm": 0.016362924128770828, |
| "learning_rate": 2.379323688349516e-06, |
| "loss": 0.0007, |
| "step": 437 |
| }, |
| { |
| "epoch": 8.76, |
| "grad_norm": 0.01405677292495966, |
| "learning_rate": 2.3055630366772856e-06, |
| "loss": 0.0007, |
| "step": 438 |
| }, |
| { |
| "epoch": 8.78, |
| "grad_norm": 0.017908280715346336, |
| "learning_rate": 2.2329084798455746e-06, |
| "loss": 0.0007, |
| "step": 439 |
| }, |
| { |
| "epoch": 8.8, |
| "grad_norm": 0.029627658426761627, |
| "learning_rate": 2.1613635589349756e-06, |
| "loss": 0.0006, |
| "step": 440 |
| }, |
| { |
| "epoch": 8.82, |
| "grad_norm": 0.009773575700819492, |
| "learning_rate": 2.0909317609440095e-06, |
| "loss": 0.0006, |
| "step": 441 |
| }, |
| { |
| "epoch": 8.84, |
| "grad_norm": 0.014441922307014465, |
| "learning_rate": 2.0216165186191407e-06, |
| "loss": 0.0007, |
| "step": 442 |
| }, |
| { |
| "epoch": 8.86, |
| "grad_norm": 0.0174330435693264, |
| "learning_rate": 1.95342121028749e-06, |
| "loss": 0.0008, |
| "step": 443 |
| }, |
| { |
| "epoch": 8.88, |
| "grad_norm": 0.018265046179294586, |
| "learning_rate": 1.8863491596921745e-06, |
| "loss": 0.0007, |
| "step": 444 |
| }, |
| { |
| "epoch": 8.9, |
| "grad_norm": 0.025862442329525948, |
| "learning_rate": 1.8204036358303173e-06, |
| "loss": 0.0006, |
| "step": 445 |
| }, |
| { |
| "epoch": 8.92, |
| "grad_norm": 0.02057448960840702, |
| "learning_rate": 1.7555878527937164e-06, |
| "loss": 0.0007, |
| "step": 446 |
| }, |
| { |
| "epoch": 8.94, |
| "grad_norm": 0.02054482139647007, |
| "learning_rate": 1.6919049696121958e-06, |
| "loss": 0.0008, |
| "step": 447 |
| }, |
| { |
| "epoch": 8.96, |
| "grad_norm": 0.031380027532577515, |
| "learning_rate": 1.629358090099639e-06, |
| "loss": 0.0008, |
| "step": 448 |
| }, |
| { |
| "epoch": 8.98, |
| "grad_norm": 0.012362498790025711, |
| "learning_rate": 1.5679502627027136e-06, |
| "loss": 0.0007, |
| "step": 449 |
| }, |
| { |
| "epoch": 9.0, |
| "grad_norm": 0.017466159537434578, |
| "learning_rate": 1.5076844803522922e-06, |
| "loss": 0.0008, |
| "step": 450 |
| }, |
| { |
| "epoch": 9.02, |
| "grad_norm": 0.0148147689178586, |
| "learning_rate": 1.4485636803175829e-06, |
| "loss": 0.0007, |
| "step": 451 |
| }, |
| { |
| "epoch": 9.04, |
| "grad_norm": 1.0861493349075317, |
| "learning_rate": 1.3905907440629752e-06, |
| "loss": 0.0006, |
| "step": 452 |
| }, |
| { |
| "epoch": 9.06, |
| "grad_norm": 0.024347692728042603, |
| "learning_rate": 1.333768497107593e-06, |
| "loss": 0.0006, |
| "step": 453 |
| }, |
| { |
| "epoch": 9.08, |
| "grad_norm": 0.02870842069387436, |
| "learning_rate": 1.2780997088875869e-06, |
| "loss": 0.0006, |
| "step": 454 |
| }, |
| { |
| "epoch": 9.1, |
| "grad_norm": 0.021804317831993103, |
| "learning_rate": 1.2235870926211619e-06, |
| "loss": 0.0006, |
| "step": 455 |
| }, |
| { |
| "epoch": 9.12, |
| "grad_norm": 0.03335144743323326, |
| "learning_rate": 1.170233305176327e-06, |
| "loss": 0.0006, |
| "step": 456 |
| }, |
| { |
| "epoch": 9.14, |
| "grad_norm": 0.01712186448276043, |
| "learning_rate": 1.1180409469414094e-06, |
| "loss": 0.0007, |
| "step": 457 |
| }, |
| { |
| "epoch": 9.16, |
| "grad_norm": 0.011126603931188583, |
| "learning_rate": 1.067012561698319e-06, |
| "loss": 0.0006, |
| "step": 458 |
| }, |
| { |
| "epoch": 9.18, |
| "grad_norm": 0.17538900673389435, |
| "learning_rate": 1.0171506364985622e-06, |
| "loss": 0.0007, |
| "step": 459 |
| }, |
| { |
| "epoch": 9.2, |
| "grad_norm": 0.012856665067374706, |
| "learning_rate": 9.684576015420278e-07, |
| "loss": 0.0006, |
| "step": 460 |
| }, |
| { |
| "epoch": 9.22, |
| "grad_norm": 0.08660769462585449, |
| "learning_rate": 9.209358300585474e-07, |
| "loss": 0.0006, |
| "step": 461 |
| }, |
| { |
| "epoch": 9.24, |
| "grad_norm": 0.013641130179166794, |
| "learning_rate": 8.745876381922147e-07, |
| "loss": 0.0006, |
| "step": 462 |
| }, |
| { |
| "epoch": 9.26, |
| "grad_norm": 0.027097051963210106, |
| "learning_rate": 8.294152848885157e-07, |
| "loss": 0.0007, |
| "step": 463 |
| }, |
| { |
| "epoch": 9.28, |
| "grad_norm": 0.016025835648179054, |
| "learning_rate": 7.854209717842231e-07, |
| "loss": 0.0005, |
| "step": 464 |
| }, |
| { |
| "epoch": 9.3, |
| "grad_norm": 0.020238352939486504, |
| "learning_rate": 7.426068431000882e-07, |
| "loss": 0.0007, |
| "step": 465 |
| }, |
| { |
| "epoch": 9.32, |
| "grad_norm": 0.013973543420433998, |
| "learning_rate": 7.009749855363456e-07, |
| "loss": 0.0006, |
| "step": 466 |
| }, |
| { |
| "epoch": 9.34, |
| "grad_norm": 0.022512558847665787, |
| "learning_rate": 6.605274281709928e-07, |
| "loss": 0.0006, |
| "step": 467 |
| }, |
| { |
| "epoch": 9.36, |
| "grad_norm": 0.015979360789060593, |
| "learning_rate": 6.212661423609184e-07, |
| "loss": 0.0007, |
| "step": 468 |
| }, |
| { |
| "epoch": 9.38, |
| "grad_norm": 0.01091644074767828, |
| "learning_rate": 5.83193041645802e-07, |
| "loss": 0.0006, |
| "step": 469 |
| }, |
| { |
| "epoch": 9.4, |
| "grad_norm": 0.011535176075994968, |
| "learning_rate": 5.463099816548579e-07, |
| "loss": 0.0006, |
| "step": 470 |
| }, |
| { |
| "epoch": 9.42, |
| "grad_norm": 0.017591234296560287, |
| "learning_rate": 5.106187600163987e-07, |
| "loss": 0.0006, |
| "step": 471 |
| }, |
| { |
| "epoch": 9.44, |
| "grad_norm": 0.020435495302081108, |
| "learning_rate": 4.7612111627021175e-07, |
| "loss": 0.0006, |
| "step": 472 |
| }, |
| { |
| "epoch": 9.46, |
| "grad_norm": 0.02458248846232891, |
| "learning_rate": 4.4281873178278475e-07, |
| "loss": 0.0006, |
| "step": 473 |
| }, |
| { |
| "epoch": 9.48, |
| "grad_norm": 0.01399570144712925, |
| "learning_rate": 4.107132296653549e-07, |
| "loss": 0.0005, |
| "step": 474 |
| }, |
| { |
| "epoch": 9.5, |
| "grad_norm": 0.011794820427894592, |
| "learning_rate": 3.7980617469479953e-07, |
| "loss": 0.0006, |
| "step": 475 |
| }, |
| { |
| "epoch": 9.52, |
| "grad_norm": 0.034110236912965775, |
| "learning_rate": 3.5009907323737825e-07, |
| "loss": 0.0007, |
| "step": 476 |
| }, |
| { |
| "epoch": 9.54, |
| "grad_norm": 0.02996162697672844, |
| "learning_rate": 3.215933731753024e-07, |
| "loss": 0.0007, |
| "step": 477 |
| }, |
| { |
| "epoch": 9.56, |
| "grad_norm": 0.01556292176246643, |
| "learning_rate": 2.942904638361804e-07, |
| "loss": 0.0006, |
| "step": 478 |
| }, |
| { |
| "epoch": 9.58, |
| "grad_norm": 0.01747916080057621, |
| "learning_rate": 2.681916759252917e-07, |
| "loss": 0.0008, |
| "step": 479 |
| }, |
| { |
| "epoch": 9.6, |
| "grad_norm": 0.016395531594753265, |
| "learning_rate": 2.4329828146074095e-07, |
| "loss": 0.0006, |
| "step": 480 |
| }, |
| { |
| "epoch": 9.62, |
| "grad_norm": 0.028636911883950233, |
| "learning_rate": 2.1961149371145795e-07, |
| "loss": 0.0007, |
| "step": 481 |
| }, |
| { |
| "epoch": 9.64, |
| "grad_norm": 0.013615133240818977, |
| "learning_rate": 1.9713246713805588e-07, |
| "loss": 0.0006, |
| "step": 482 |
| }, |
| { |
| "epoch": 9.66, |
| "grad_norm": 0.014773129485547543, |
| "learning_rate": 1.7586229733657644e-07, |
| "loss": 0.0006, |
| "step": 483 |
| }, |
| { |
| "epoch": 9.68, |
| "grad_norm": 0.013628330081701279, |
| "learning_rate": 1.5580202098509077e-07, |
| "loss": 0.0007, |
| "step": 484 |
| }, |
| { |
| "epoch": 9.7, |
| "grad_norm": 0.013818751089274883, |
| "learning_rate": 1.3695261579316777e-07, |
| "loss": 0.0006, |
| "step": 485 |
| }, |
| { |
| "epoch": 9.72, |
| "grad_norm": 0.01693764328956604, |
| "learning_rate": 1.193150004542204e-07, |
| "loss": 0.0006, |
| "step": 486 |
| }, |
| { |
| "epoch": 9.74, |
| "grad_norm": 0.018511202186346054, |
| "learning_rate": 1.0289003460074165e-07, |
| "loss": 0.0007, |
| "step": 487 |
| }, |
| { |
| "epoch": 9.76, |
| "grad_norm": 0.057176489382982254, |
| "learning_rate": 8.767851876239074e-08, |
| "loss": 0.0007, |
| "step": 488 |
| }, |
| { |
| "epoch": 9.78, |
| "grad_norm": 0.01059312280267477, |
| "learning_rate": 7.368119432699383e-08, |
| "loss": 0.0006, |
| "step": 489 |
| }, |
| { |
| "epoch": 9.8, |
| "grad_norm": 0.014415513724088669, |
| "learning_rate": 6.089874350439506e-08, |
| "loss": 0.0006, |
| "step": 490 |
| }, |
| { |
| "epoch": 9.82, |
| "grad_norm": 0.014411581680178642, |
| "learning_rate": 4.9331789293211026e-08, |
| "loss": 0.0006, |
| "step": 491 |
| }, |
| { |
| "epoch": 9.84, |
| "grad_norm": 0.020400647073984146, |
| "learning_rate": 3.8980895450474455e-08, |
| "loss": 0.0007, |
| "step": 492 |
| }, |
| { |
| "epoch": 9.86, |
| "grad_norm": 0.01764337532222271, |
| "learning_rate": 2.9846566464150626e-08, |
| "loss": 0.0006, |
| "step": 493 |
| }, |
| { |
| "epoch": 9.88, |
| "grad_norm": 0.013475135900080204, |
| "learning_rate": 2.192924752854042e-08, |
| "loss": 0.0006, |
| "step": 494 |
| }, |
| { |
| "epoch": 9.9, |
| "grad_norm": 0.020350459963083267, |
| "learning_rate": 1.522932452260595e-08, |
| "loss": 0.0006, |
| "step": 495 |
| }, |
| { |
| "epoch": 9.92, |
| "grad_norm": 0.014247527346014977, |
| "learning_rate": 9.747123991141194e-09, |
| "loss": 0.0006, |
| "step": 496 |
| }, |
| { |
| "epoch": 9.94, |
| "grad_norm": 0.024135878309607506, |
| "learning_rate": 5.48291312886251e-09, |
| "loss": 0.0007, |
| "step": 497 |
| }, |
| { |
| "epoch": 9.96, |
| "grad_norm": 0.01212978269904852, |
| "learning_rate": 2.4368997673940297e-09, |
| "loss": 0.0006, |
| "step": 498 |
| }, |
| { |
| "epoch": 9.98, |
| "grad_norm": 0.01443579513579607, |
| "learning_rate": 6.092323651313292e-10, |
| "loss": 0.0007, |
| "step": 499 |
| }, |
| { |
| "epoch": 10.0, |
| "grad_norm": 0.01410845760256052, |
| "learning_rate": 0.0, |
| "loss": 0.0007, |
| "step": 500 |
| }, |
| { |
| "epoch": 10.0, |
| "step": 500, |
| "total_flos": 1.13782877585408e+18, |
| "train_loss": 0.07423569742811378, |
| "train_runtime": 7287.0887, |
| "train_samples_per_second": 4.384, |
| "train_steps_per_second": 0.069 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 500, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.13782877585408e+18, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
