| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 37, | |
| "global_step": 290, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006896551724137931, | |
| "grad_norm": 2.651252269744873, | |
| "learning_rate": 7.5e-07, | |
| "loss": 4.7891, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006896551724137931, | |
| "eval_loss": 3.3850624561309814, | |
| "eval_runtime": 4.5511, | |
| "eval_samples_per_second": 1.758, | |
| "eval_steps_per_second": 1.758, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013793103448275862, | |
| "grad_norm": 2.064390182495117, | |
| "learning_rate": 1.5e-06, | |
| "loss": 2.9792, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.020689655172413793, | |
| "grad_norm": 1.254639983177185, | |
| "learning_rate": 2.25e-06, | |
| "loss": 3.0642, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.027586206896551724, | |
| "grad_norm": 1.5396596193313599, | |
| "learning_rate": 3e-06, | |
| "loss": 3.249, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.034482758620689655, | |
| "grad_norm": 2.1187007427215576, | |
| "learning_rate": 3.75e-06, | |
| "loss": 3.4551, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.041379310344827586, | |
| "grad_norm": 3.609483003616333, | |
| "learning_rate": 4.5e-06, | |
| "loss": 6.0963, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.04827586206896552, | |
| "grad_norm": 2.3606605529785156, | |
| "learning_rate": 5.25e-06, | |
| "loss": 4.5106, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.05517241379310345, | |
| "grad_norm": 1.5973587036132812, | |
| "learning_rate": 6e-06, | |
| "loss": 3.3045, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06206896551724138, | |
| "grad_norm": 1.4481266736984253, | |
| "learning_rate": 6.750000000000001e-06, | |
| "loss": 3.5009, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06896551724137931, | |
| "grad_norm": 2.194455862045288, | |
| "learning_rate": 7.5e-06, | |
| "loss": 5.0099, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07586206896551724, | |
| "grad_norm": 2.1214380264282227, | |
| "learning_rate": 8.25e-06, | |
| "loss": 3.7116, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.08275862068965517, | |
| "grad_norm": 1.501364827156067, | |
| "learning_rate": 9e-06, | |
| "loss": 3.3266, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0896551724137931, | |
| "grad_norm": 2.078202962875366, | |
| "learning_rate": 9.75e-06, | |
| "loss": 3.4969, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.09655172413793103, | |
| "grad_norm": 1.9757059812545776, | |
| "learning_rate": 1.05e-05, | |
| "loss": 3.3945, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.10344827586206896, | |
| "grad_norm": 2.730952739715576, | |
| "learning_rate": 1.125e-05, | |
| "loss": 3.5526, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1103448275862069, | |
| "grad_norm": 3.307832717895508, | |
| "learning_rate": 1.2e-05, | |
| "loss": 4.7907, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.11724137931034483, | |
| "grad_norm": 2.1818623542785645, | |
| "learning_rate": 1.275e-05, | |
| "loss": 3.9304, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.12413793103448276, | |
| "grad_norm": 3.2467010021209717, | |
| "learning_rate": 1.3500000000000001e-05, | |
| "loss": 4.9399, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1310344827586207, | |
| "grad_norm": 1.985250473022461, | |
| "learning_rate": 1.4249999999999999e-05, | |
| "loss": 2.9249, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.13793103448275862, | |
| "grad_norm": 2.669128894805908, | |
| "learning_rate": 1.5e-05, | |
| "loss": 3.33, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14482758620689656, | |
| "grad_norm": 2.3027143478393555, | |
| "learning_rate": 1.575e-05, | |
| "loss": 2.6643, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.15172413793103448, | |
| "grad_norm": 3.2221450805664062, | |
| "learning_rate": 1.65e-05, | |
| "loss": 3.6538, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.15862068965517243, | |
| "grad_norm": 4.213558197021484, | |
| "learning_rate": 1.725e-05, | |
| "loss": 3.5537, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.16551724137931034, | |
| "grad_norm": 1.8173574209213257, | |
| "learning_rate": 1.8e-05, | |
| "loss": 2.9893, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1724137931034483, | |
| "grad_norm": 2.863757610321045, | |
| "learning_rate": 1.8750000000000002e-05, | |
| "loss": 2.487, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1793103448275862, | |
| "grad_norm": 2.650667905807495, | |
| "learning_rate": 1.95e-05, | |
| "loss": 2.4155, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.18620689655172415, | |
| "grad_norm": 2.5865488052368164, | |
| "learning_rate": 2.025e-05, | |
| "loss": 2.6802, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.19310344827586207, | |
| "grad_norm": 2.5942306518554688, | |
| "learning_rate": 2.1e-05, | |
| "loss": 2.6337, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 4.72637414932251, | |
| "learning_rate": 2.175e-05, | |
| "loss": 4.4921, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.20689655172413793, | |
| "grad_norm": 3.370011806488037, | |
| "learning_rate": 2.25e-05, | |
| "loss": 2.8945, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.21379310344827587, | |
| "grad_norm": 2.9828832149505615, | |
| "learning_rate": 2.3250000000000003e-05, | |
| "loss": 3.031, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.2206896551724138, | |
| "grad_norm": 2.9294815063476562, | |
| "learning_rate": 2.4e-05, | |
| "loss": 2.7564, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.22758620689655173, | |
| "grad_norm": 2.9029836654663086, | |
| "learning_rate": 2.475e-05, | |
| "loss": 2.635, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.23448275862068965, | |
| "grad_norm": 3.5925707817077637, | |
| "learning_rate": 2.55e-05, | |
| "loss": 2.9502, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.2413793103448276, | |
| "grad_norm": 4.757285118103027, | |
| "learning_rate": 2.625e-05, | |
| "loss": 2.0215, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2482758620689655, | |
| "grad_norm": 12.417799949645996, | |
| "learning_rate": 2.7000000000000002e-05, | |
| "loss": 4.3027, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.25517241379310346, | |
| "grad_norm": 4.293732166290283, | |
| "learning_rate": 2.7750000000000004e-05, | |
| "loss": 1.8095, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.25517241379310346, | |
| "eval_loss": 2.7702932357788086, | |
| "eval_runtime": 4.4922, | |
| "eval_samples_per_second": 1.781, | |
| "eval_steps_per_second": 1.781, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.2620689655172414, | |
| "grad_norm": 4.490789890289307, | |
| "learning_rate": 2.8499999999999998e-05, | |
| "loss": 2.2294, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.2689655172413793, | |
| "grad_norm": 6.464705467224121, | |
| "learning_rate": 2.925e-05, | |
| "loss": 1.8365, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.27586206896551724, | |
| "grad_norm": 4.536788463592529, | |
| "learning_rate": 3e-05, | |
| "loss": 2.3919, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2827586206896552, | |
| "grad_norm": 4.616312503814697, | |
| "learning_rate": 2.9999842246463293e-05, | |
| "loss": 2.7667, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.2896551724137931, | |
| "grad_norm": 9.268322944641113, | |
| "learning_rate": 2.9999368989171332e-05, | |
| "loss": 1.6036, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.296551724137931, | |
| "grad_norm": 9.249737739562988, | |
| "learning_rate": 2.9998580238078518e-05, | |
| "loss": 3.5214, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.30344827586206896, | |
| "grad_norm": 5.715229034423828, | |
| "learning_rate": 2.9997476009775285e-05, | |
| "loss": 2.8424, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.3103448275862069, | |
| "grad_norm": 11.085472106933594, | |
| "learning_rate": 2.999605632748776e-05, | |
| "loss": 3.2402, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.31724137931034485, | |
| "grad_norm": 9.64968204498291, | |
| "learning_rate": 2.999432122107726e-05, | |
| "loss": 2.5156, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.32413793103448274, | |
| "grad_norm": 5.387156963348389, | |
| "learning_rate": 2.9992270727039674e-05, | |
| "loss": 2.5335, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.3310344827586207, | |
| "grad_norm": 8.309078216552734, | |
| "learning_rate": 2.9989904888504697e-05, | |
| "loss": 3.9152, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.33793103448275863, | |
| "grad_norm": 8.13180923461914, | |
| "learning_rate": 2.998722375523491e-05, | |
| "loss": 2.6522, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.3448275862068966, | |
| "grad_norm": 5.079596042633057, | |
| "learning_rate": 2.9984227383624753e-05, | |
| "loss": 2.1673, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.35172413793103446, | |
| "grad_norm": 4.810355186462402, | |
| "learning_rate": 2.9980915836699322e-05, | |
| "loss": 2.4192, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.3586206896551724, | |
| "grad_norm": 5.691514015197754, | |
| "learning_rate": 2.9977289184113038e-05, | |
| "loss": 2.1087, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.36551724137931035, | |
| "grad_norm": 6.280345439910889, | |
| "learning_rate": 2.997334750214822e-05, | |
| "loss": 2.1365, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.3724137931034483, | |
| "grad_norm": 5.447160243988037, | |
| "learning_rate": 2.9969090873713425e-05, | |
| "loss": 2.3364, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.3793103448275862, | |
| "grad_norm": 9.810458183288574, | |
| "learning_rate": 2.9964519388341753e-05, | |
| "loss": 2.6459, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.38620689655172413, | |
| "grad_norm": 8.42009449005127, | |
| "learning_rate": 2.9959633142188928e-05, | |
| "loss": 2.449, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.3931034482758621, | |
| "grad_norm": 4.881720066070557, | |
| "learning_rate": 2.99544322380313e-05, | |
| "loss": 2.1418, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 5.82330322265625, | |
| "learning_rate": 2.994891678526368e-05, | |
| "loss": 1.7012, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.4068965517241379, | |
| "grad_norm": 7.9598917961120605, | |
| "learning_rate": 2.994308689989702e-05, | |
| "loss": 1.935, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.41379310344827586, | |
| "grad_norm": 4.582525253295898, | |
| "learning_rate": 2.9936942704555988e-05, | |
| "loss": 2.3673, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.4206896551724138, | |
| "grad_norm": 5.968487739562988, | |
| "learning_rate": 2.9930484328476392e-05, | |
| "loss": 1.3351, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.42758620689655175, | |
| "grad_norm": 6.217311859130859, | |
| "learning_rate": 2.992371190750246e-05, | |
| "loss": 2.8033, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.43448275862068964, | |
| "grad_norm": 15.824493408203125, | |
| "learning_rate": 2.9916625584083965e-05, | |
| "loss": 3.5775, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.4413793103448276, | |
| "grad_norm": 6.833436965942383, | |
| "learning_rate": 2.990922550727326e-05, | |
| "loss": 3.1572, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.4482758620689655, | |
| "grad_norm": 7.139071464538574, | |
| "learning_rate": 2.9901511832722107e-05, | |
| "loss": 2.5818, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.45517241379310347, | |
| "grad_norm": 5.222311973571777, | |
| "learning_rate": 2.989348472267844e-05, | |
| "loss": 1.6886, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.46206896551724136, | |
| "grad_norm": 5.626909255981445, | |
| "learning_rate": 2.988514434598292e-05, | |
| "loss": 2.3763, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.4689655172413793, | |
| "grad_norm": 4.76120138168335, | |
| "learning_rate": 2.9876490878065402e-05, | |
| "loss": 2.3714, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.47586206896551725, | |
| "grad_norm": 4.187699317932129, | |
| "learning_rate": 2.9867524500941255e-05, | |
| "loss": 1.5454, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.4827586206896552, | |
| "grad_norm": 6.578094959259033, | |
| "learning_rate": 2.9858245403207488e-05, | |
| "loss": 2.9233, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.4896551724137931, | |
| "grad_norm": 21.87733268737793, | |
| "learning_rate": 2.9848653780038844e-05, | |
| "loss": 3.232, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.496551724137931, | |
| "grad_norm": 8.493062973022461, | |
| "learning_rate": 2.9838749833183647e-05, | |
| "loss": 2.1025, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.503448275862069, | |
| "grad_norm": 9.408147811889648, | |
| "learning_rate": 2.9828533770959584e-05, | |
| "loss": 1.8301, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.5103448275862069, | |
| "grad_norm": 5.230013847351074, | |
| "learning_rate": 2.9818005808249323e-05, | |
| "loss": 1.6428, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.5103448275862069, | |
| "eval_loss": 2.1590590476989746, | |
| "eval_runtime": 4.4994, | |
| "eval_samples_per_second": 1.778, | |
| "eval_steps_per_second": 1.778, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.5172413793103449, | |
| "grad_norm": 5.788967132568359, | |
| "learning_rate": 2.9807166166495966e-05, | |
| "loss": 0.9333, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.5241379310344828, | |
| "grad_norm": 5.982523441314697, | |
| "learning_rate": 2.979601507369843e-05, | |
| "loss": 1.8066, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.5310344827586206, | |
| "grad_norm": 4.951727867126465, | |
| "learning_rate": 2.978455276440662e-05, | |
| "loss": 1.3418, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.5379310344827586, | |
| "grad_norm": 5.705328941345215, | |
| "learning_rate": 2.977277947971652e-05, | |
| "loss": 1.1168, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.5448275862068965, | |
| "grad_norm": 10.673117637634277, | |
| "learning_rate": 2.9760695467265096e-05, | |
| "loss": 1.9509, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.5517241379310345, | |
| "grad_norm": 7.005712985992432, | |
| "learning_rate": 2.9748300981225112e-05, | |
| "loss": 2.8095, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5586206896551724, | |
| "grad_norm": 10.768919944763184, | |
| "learning_rate": 2.9735596282299767e-05, | |
| "loss": 1.1537, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.5655172413793104, | |
| "grad_norm": 5.258718967437744, | |
| "learning_rate": 2.9722581637717225e-05, | |
| "loss": 2.0656, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.5724137931034483, | |
| "grad_norm": 6.1790971755981445, | |
| "learning_rate": 2.9709257321224973e-05, | |
| "loss": 2.4952, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.5793103448275863, | |
| "grad_norm": 5.152263164520264, | |
| "learning_rate": 2.9695623613084094e-05, | |
| "loss": 1.631, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.5862068965517241, | |
| "grad_norm": 9.117701530456543, | |
| "learning_rate": 2.9681680800063333e-05, | |
| "loss": 1.5723, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.593103448275862, | |
| "grad_norm": 15.927285194396973, | |
| "learning_rate": 2.966742917543311e-05, | |
| "loss": 4.0567, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 7.300537109375, | |
| "learning_rate": 2.9652869038959308e-05, | |
| "loss": 2.0857, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.6068965517241379, | |
| "grad_norm": 5.633571147918701, | |
| "learning_rate": 2.9638000696897004e-05, | |
| "loss": 1.5046, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.6137931034482759, | |
| "grad_norm": 5.7234625816345215, | |
| "learning_rate": 2.9622824461984e-05, | |
| "loss": 2.1678, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.6206896551724138, | |
| "grad_norm": 5.1384124755859375, | |
| "learning_rate": 2.9607340653434263e-05, | |
| "loss": 1.2331, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.6275862068965518, | |
| "grad_norm": 9.393917083740234, | |
| "learning_rate": 2.9591549596931196e-05, | |
| "loss": 2.3239, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.6344827586206897, | |
| "grad_norm": 29.67850112915039, | |
| "learning_rate": 2.957545162462081e-05, | |
| "loss": 2.7711, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.6413793103448275, | |
| "grad_norm": 11.757678985595703, | |
| "learning_rate": 2.95590470751047e-05, | |
| "loss": 0.862, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.6482758620689655, | |
| "grad_norm": 5.055336952209473, | |
| "learning_rate": 2.954233629343297e-05, | |
| "loss": 0.7167, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.6551724137931034, | |
| "grad_norm": 6.484320640563965, | |
| "learning_rate": 2.9525319631096936e-05, | |
| "loss": 1.518, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.6620689655172414, | |
| "grad_norm": 21.282947540283203, | |
| "learning_rate": 2.950799744602176e-05, | |
| "loss": 1.6637, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.6689655172413793, | |
| "grad_norm": 4.83950662612915, | |
| "learning_rate": 2.94903701025589e-05, | |
| "loss": 1.8401, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.6758620689655173, | |
| "grad_norm": 8.747105598449707, | |
| "learning_rate": 2.9472437971478456e-05, | |
| "loss": 2.6096, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.6827586206896552, | |
| "grad_norm": 5.483854293823242, | |
| "learning_rate": 2.9454201429961377e-05, | |
| "loss": 1.1973, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.6896551724137931, | |
| "grad_norm": 8.147703170776367, | |
| "learning_rate": 2.9435660861591523e-05, | |
| "loss": 2.2331, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.696551724137931, | |
| "grad_norm": 10.85132884979248, | |
| "learning_rate": 2.9416816656347585e-05, | |
| "loss": 1.3165, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.7034482758620689, | |
| "grad_norm": 9.249916076660156, | |
| "learning_rate": 2.9397669210594905e-05, | |
| "loss": 2.4115, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.7103448275862069, | |
| "grad_norm": 8.229886054992676, | |
| "learning_rate": 2.9378218927077116e-05, | |
| "loss": 1.3861, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.7172413793103448, | |
| "grad_norm": 5.1249613761901855, | |
| "learning_rate": 2.9358466214907692e-05, | |
| "loss": 1.3119, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.7241379310344828, | |
| "grad_norm": 7.522292137145996, | |
| "learning_rate": 2.9338411489561327e-05, | |
| "loss": 2.3285, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.7310344827586207, | |
| "grad_norm": 8.781840324401855, | |
| "learning_rate": 2.931805517286519e-05, | |
| "loss": 2.3725, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.7379310344827587, | |
| "grad_norm": 8.974847793579102, | |
| "learning_rate": 2.929739769299009e-05, | |
| "loss": 2.7679, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.7448275862068966, | |
| "grad_norm": 13.757139205932617, | |
| "learning_rate": 2.927643948444142e-05, | |
| "loss": 2.8373, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.7517241379310344, | |
| "grad_norm": 6.372509956359863, | |
| "learning_rate": 2.925518098805005e-05, | |
| "loss": 0.3335, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.7586206896551724, | |
| "grad_norm": 18.51079750061035, | |
| "learning_rate": 2.9233622650963046e-05, | |
| "loss": 3.7183, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.7655172413793103, | |
| "grad_norm": 7.130232810974121, | |
| "learning_rate": 2.921176492663426e-05, | |
| "loss": 2.7397, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.7655172413793103, | |
| "eval_loss": 2.076895236968994, | |
| "eval_runtime": 4.5121, | |
| "eval_samples_per_second": 1.773, | |
| "eval_steps_per_second": 1.773, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.7724137931034483, | |
| "grad_norm": 5.484634876251221, | |
| "learning_rate": 2.9189608274814813e-05, | |
| "loss": 1.0504, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.7793103448275862, | |
| "grad_norm": 7.2361979484558105, | |
| "learning_rate": 2.916715316154339e-05, | |
| "loss": 1.2353, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.7862068965517242, | |
| "grad_norm": 5.681639194488525, | |
| "learning_rate": 2.9144400059136457e-05, | |
| "loss": 1.5471, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.7931034482758621, | |
| "grad_norm": 8.158857345581055, | |
| "learning_rate": 2.9121349446178338e-05, | |
| "loss": 2.4476, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 6.511702537536621, | |
| "learning_rate": 2.909800180751112e-05, | |
| "loss": 1.1023, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.8068965517241379, | |
| "grad_norm": 9.999719619750977, | |
| "learning_rate": 2.907435763422449e-05, | |
| "loss": 0.5992, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.8137931034482758, | |
| "grad_norm": 7.8701171875, | |
| "learning_rate": 2.9050417423645374e-05, | |
| "loss": 1.6095, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.8206896551724138, | |
| "grad_norm": 6.189757823944092, | |
| "learning_rate": 2.9026181679327483e-05, | |
| "loss": 1.5167, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.8275862068965517, | |
| "grad_norm": 17.398225784301758, | |
| "learning_rate": 2.9001650911040744e-05, | |
| "loss": 1.3394, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.8344827586206897, | |
| "grad_norm": 13.492450714111328, | |
| "learning_rate": 2.897682563476054e-05, | |
| "loss": 5.1631, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.8413793103448276, | |
| "grad_norm": 6.701801776885986, | |
| "learning_rate": 2.8951706372656898e-05, | |
| "loss": 1.4963, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.8482758620689655, | |
| "grad_norm": 11.134561538696289, | |
| "learning_rate": 2.8926293653083475e-05, | |
| "loss": 2.0888, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.8551724137931035, | |
| "grad_norm": 5.3243608474731445, | |
| "learning_rate": 2.890058801056645e-05, | |
| "loss": 1.9287, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.8620689655172413, | |
| "grad_norm": 5.231749057769775, | |
| "learning_rate": 2.8874589985793298e-05, | |
| "loss": 1.543, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.8689655172413793, | |
| "grad_norm": 29.016874313354492, | |
| "learning_rate": 2.88483001256014e-05, | |
| "loss": 3.8339, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.8758620689655172, | |
| "grad_norm": 5.226491451263428, | |
| "learning_rate": 2.8821718982966544e-05, | |
| "loss": 1.189, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.8827586206896552, | |
| "grad_norm": 5.349326133728027, | |
| "learning_rate": 2.87948471169913e-05, | |
| "loss": 0.4606, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.8896551724137931, | |
| "grad_norm": 8.602606773376465, | |
| "learning_rate": 2.8767685092893244e-05, | |
| "loss": 3.0269, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.896551724137931, | |
| "grad_norm": 8.23015308380127, | |
| "learning_rate": 2.874023348199311e-05, | |
| "loss": 1.2428, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.903448275862069, | |
| "grad_norm": 5.327670097351074, | |
| "learning_rate": 2.8712492861702712e-05, | |
| "loss": 0.9737, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.9103448275862069, | |
| "grad_norm": 4.516807556152344, | |
| "learning_rate": 2.868446381551285e-05, | |
| "loss": 1.2708, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.9172413793103448, | |
| "grad_norm": 7.308916091918945, | |
| "learning_rate": 2.865614693298101e-05, | |
| "loss": 2.5184, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.9241379310344827, | |
| "grad_norm": 7.566427230834961, | |
| "learning_rate": 2.8627542809718972e-05, | |
| "loss": 1.4915, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.9310344827586207, | |
| "grad_norm": 6.399407863616943, | |
| "learning_rate": 2.8598652047380292e-05, | |
| "loss": 1.9207, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.9379310344827586, | |
| "grad_norm": 5.2886786460876465, | |
| "learning_rate": 2.8569475253647624e-05, | |
| "loss": 1.0044, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.9448275862068966, | |
| "grad_norm": 4.2925310134887695, | |
| "learning_rate": 2.854001304221995e-05, | |
| "loss": 1.6515, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.9517241379310345, | |
| "grad_norm": 3.5389490127563477, | |
| "learning_rate": 2.8510266032799688e-05, | |
| "loss": 0.624, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.9586206896551724, | |
| "grad_norm": 5.259653568267822, | |
| "learning_rate": 2.8480234851079622e-05, | |
| "loss": 1.5153, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.9655172413793104, | |
| "grad_norm": 7.633677959442139, | |
| "learning_rate": 2.8449920128729772e-05, | |
| "loss": 1.6288, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.9724137931034482, | |
| "grad_norm": 7.951615333557129, | |
| "learning_rate": 2.841932250338409e-05, | |
| "loss": 2.4153, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.9793103448275862, | |
| "grad_norm": 4.297111511230469, | |
| "learning_rate": 2.8388442618627063e-05, | |
| "loss": 0.4714, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.9862068965517241, | |
| "grad_norm": 5.56075382232666, | |
| "learning_rate": 2.8357281123980153e-05, | |
| "loss": 1.3144, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.993103448275862, | |
| "grad_norm": 7.056431293487549, | |
| "learning_rate": 2.8325838674888168e-05, | |
| "loss": 2.9863, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 5.265207290649414, | |
| "learning_rate": 2.829411593270545e-05, | |
| "loss": 1.8668, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.006896551724138, | |
| "grad_norm": 6.738914966583252, | |
| "learning_rate": 2.826211356468196e-05, | |
| "loss": 1.6213, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 1.013793103448276, | |
| "grad_norm": 19.16160774230957, | |
| "learning_rate": 2.822983224394926e-05, | |
| "loss": 1.2061, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 1.0206896551724138, | |
| "grad_norm": 6.643246173858643, | |
| "learning_rate": 2.8197272649506363e-05, | |
| "loss": 1.936, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 1.0206896551724138, | |
| "eval_loss": 1.9735311269760132, | |
| "eval_runtime": 4.4975, | |
| "eval_samples_per_second": 1.779, | |
| "eval_steps_per_second": 1.779, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 1.0275862068965518, | |
| "grad_norm": 5.578238010406494, | |
| "learning_rate": 2.8164435466205423e-05, | |
| "loss": 1.7389, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 1.0344827586206897, | |
| "grad_norm": 10.583780288696289, | |
| "learning_rate": 2.8131321384737344e-05, | |
| "loss": 0.4309, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.0413793103448277, | |
| "grad_norm": 7.088948726654053, | |
| "learning_rate": 2.809793110161725e-05, | |
| "loss": 2.5514, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 1.0482758620689656, | |
| "grad_norm": 5.819264888763428, | |
| "learning_rate": 2.8064265319169854e-05, | |
| "loss": 1.3072, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 1.0551724137931036, | |
| "grad_norm": 6.2393364906311035, | |
| "learning_rate": 2.803032474551465e-05, | |
| "loss": 1.2324, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 1.0620689655172413, | |
| "grad_norm": 4.304983139038086, | |
| "learning_rate": 2.799611009455104e-05, | |
| "loss": 0.1901, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 1.0689655172413792, | |
| "grad_norm": 5.9356865882873535, | |
| "learning_rate": 2.7961622085943317e-05, | |
| "loss": 1.7746, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.0758620689655172, | |
| "grad_norm": 5.441093444824219, | |
| "learning_rate": 2.792686144510553e-05, | |
| "loss": 1.9543, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 1.0827586206896551, | |
| "grad_norm": 6.648105144500732, | |
| "learning_rate": 2.789182890318621e-05, | |
| "loss": 2.7205, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 1.089655172413793, | |
| "grad_norm": 44.886863708496094, | |
| "learning_rate": 2.785652519705301e-05, | |
| "loss": 3.465, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 1.096551724137931, | |
| "grad_norm": 5.482683181762695, | |
| "learning_rate": 2.78209510692772e-05, | |
| "loss": 1.4479, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 1.103448275862069, | |
| "grad_norm": 7.18867826461792, | |
| "learning_rate": 2.778510726811804e-05, | |
| "loss": 2.3233, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.110344827586207, | |
| "grad_norm": 10.170475006103516, | |
| "learning_rate": 2.7748994547507052e-05, | |
| "loss": 1.4287, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 1.1172413793103448, | |
| "grad_norm": 16.519548416137695, | |
| "learning_rate": 2.7712613667032156e-05, | |
| "loss": 2.0423, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 1.1241379310344828, | |
| "grad_norm": 6.548756122589111, | |
| "learning_rate": 2.7675965391921692e-05, | |
| "loss": 0.8162, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 1.1310344827586207, | |
| "grad_norm": 10.879814147949219, | |
| "learning_rate": 2.763905049302833e-05, | |
| "loss": 2.0672, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 1.1379310344827587, | |
| "grad_norm": 6.071365833282471, | |
| "learning_rate": 2.7601869746812855e-05, | |
| "loss": 1.5196, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.1448275862068966, | |
| "grad_norm": 6.293059349060059, | |
| "learning_rate": 2.7564423935327817e-05, | |
| "loss": 0.7617, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 1.1517241379310346, | |
| "grad_norm": 8.047264099121094, | |
| "learning_rate": 2.7526713846201118e-05, | |
| "loss": 0.4147, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 1.1586206896551725, | |
| "grad_norm": 3.7810680866241455, | |
| "learning_rate": 2.7488740272619413e-05, | |
| "loss": 1.0664, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 1.1655172413793102, | |
| "grad_norm": 6.20160436630249, | |
| "learning_rate": 2.7450504013311443e-05, | |
| "loss": 1.9879, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 1.1724137931034484, | |
| "grad_norm": 6.690729141235352, | |
| "learning_rate": 2.7412005872531222e-05, | |
| "loss": 1.4968, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.1793103448275861, | |
| "grad_norm": 9.275552749633789, | |
| "learning_rate": 2.737324666004113e-05, | |
| "loss": 4.3534, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 1.186206896551724, | |
| "grad_norm": 5.3003106117248535, | |
| "learning_rate": 2.7334227191094885e-05, | |
| "loss": 0.9354, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 1.193103448275862, | |
| "grad_norm": 6.302150726318359, | |
| "learning_rate": 2.729494828642038e-05, | |
| "loss": 1.2665, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 7.4209303855896, | |
| "learning_rate": 2.7255410772202435e-05, | |
| "loss": 1.5308, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 1.206896551724138, | |
| "grad_norm": 8.516342163085938, | |
| "learning_rate": 2.7215615480065415e-05, | |
| "loss": 1.1144, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.2137931034482758, | |
| "grad_norm": 4.906225204467773, | |
| "learning_rate": 2.7175563247055723e-05, | |
| "loss": 2.0357, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 1.2206896551724138, | |
| "grad_norm": 5.213315010070801, | |
| "learning_rate": 2.7135254915624213e-05, | |
| "loss": 1.6, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 1.2275862068965517, | |
| "grad_norm": 6.571521282196045, | |
| "learning_rate": 2.709469133360847e-05, | |
| "loss": 1.4624, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 1.2344827586206897, | |
| "grad_norm": 3.46243953704834, | |
| "learning_rate": 2.7053873354214957e-05, | |
| "loss": 0.3171, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 1.2413793103448276, | |
| "grad_norm": 5.865048885345459, | |
| "learning_rate": 2.7012801836001098e-05, | |
| "loss": 1.9204, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.2482758620689656, | |
| "grad_norm": 6.989517688751221, | |
| "learning_rate": 2.6971477642857185e-05, | |
| "loss": 1.518, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 1.2551724137931035, | |
| "grad_norm": 4.894804000854492, | |
| "learning_rate": 2.6929901643988237e-05, | |
| "loss": 0.8945, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 1.2620689655172415, | |
| "grad_norm": 4.024252414703369, | |
| "learning_rate": 2.6888074713895705e-05, | |
| "loss": 0.9237, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 1.2689655172413792, | |
| "grad_norm": 6.457338333129883, | |
| "learning_rate": 2.6845997732359074e-05, | |
| "loss": 2.3232, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 1.2758620689655173, | |
| "grad_norm": 7.112627029418945, | |
| "learning_rate": 2.680367158441736e-05, | |
| "loss": 0.2386, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.2758620689655173, | |
| "eval_loss": 1.9213309288024902, | |
| "eval_runtime": 4.497, | |
| "eval_samples_per_second": 1.779, | |
| "eval_steps_per_second": 1.779, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.282758620689655, | |
| "grad_norm": 15.904428482055664, | |
| "learning_rate": 2.676109716035051e-05, | |
| "loss": 1.914, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 1.2896551724137932, | |
| "grad_norm": 6.568241596221924, | |
| "learning_rate": 2.6718275355660643e-05, | |
| "loss": 0.952, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 1.296551724137931, | |
| "grad_norm": 10.139225959777832, | |
| "learning_rate": 2.667520707105325e-05, | |
| "loss": 2.1507, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 1.303448275862069, | |
| "grad_norm": 6.300340175628662, | |
| "learning_rate": 2.6631893212418227e-05, | |
| "loss": 1.8095, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 1.3103448275862069, | |
| "grad_norm": 4.754003047943115, | |
| "learning_rate": 2.6588334690810826e-05, | |
| "loss": 1.2223, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.3172413793103448, | |
| "grad_norm": 5.433348655700684, | |
| "learning_rate": 2.654453242243249e-05, | |
| "loss": 0.9192, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 1.3241379310344827, | |
| "grad_norm": 14.02868366241455, | |
| "learning_rate": 2.6500487328611584e-05, | |
| "loss": 1.642, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 1.3310344827586207, | |
| "grad_norm": 4.654847621917725, | |
| "learning_rate": 2.645620033578402e-05, | |
| "loss": 1.6479, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 1.3379310344827586, | |
| "grad_norm": 6.280045509338379, | |
| "learning_rate": 2.6411672375473768e-05, | |
| "loss": 1.9089, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 1.3448275862068966, | |
| "grad_norm": 6.455976486206055, | |
| "learning_rate": 2.6366904384273252e-05, | |
| "loss": 0.8846, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.3517241379310345, | |
| "grad_norm": 13.289530754089355, | |
| "learning_rate": 2.6321897303823665e-05, | |
| "loss": 1.32, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 1.3586206896551725, | |
| "grad_norm": 16.279457092285156, | |
| "learning_rate": 2.6276652080795157e-05, | |
| "loss": 0.7443, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 1.3655172413793104, | |
| "grad_norm": 5.546213626861572, | |
| "learning_rate": 2.6231169666866928e-05, | |
| "loss": 1.777, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 1.3724137931034484, | |
| "grad_norm": 6.5098748207092285, | |
| "learning_rate": 2.6185451018707188e-05, | |
| "loss": 0.1505, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 1.3793103448275863, | |
| "grad_norm": 7.808483123779297, | |
| "learning_rate": 2.613949709795307e-05, | |
| "loss": 2.0242, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.386206896551724, | |
| "grad_norm": 19.0113582611084, | |
| "learning_rate": 2.6093308871190376e-05, | |
| "loss": 0.5734, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 1.3931034482758622, | |
| "grad_norm": 5.4320268630981445, | |
| "learning_rate": 2.6046887309933252e-05, | |
| "loss": 1.9298, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 5.639513969421387, | |
| "learning_rate": 2.6000233390603764e-05, | |
| "loss": 2.1008, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 1.4068965517241379, | |
| "grad_norm": 6.506295680999756, | |
| "learning_rate": 2.595334809451135e-05, | |
| "loss": 2.0629, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 1.4137931034482758, | |
| "grad_norm": 6.257269382476807, | |
| "learning_rate": 2.590623240783217e-05, | |
| "loss": 0.9089, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 1.4206896551724137, | |
| "grad_norm": 7.4428534507751465, | |
| "learning_rate": 2.5858887321588403e-05, | |
| "loss": 1.6967, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 1.4275862068965517, | |
| "grad_norm": 7.234190464019775, | |
| "learning_rate": 2.5811313831627343e-05, | |
| "loss": 1.1008, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 1.4344827586206896, | |
| "grad_norm": 4.542428493499756, | |
| "learning_rate": 2.5763512938600496e-05, | |
| "loss": 1.0296, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 1.4413793103448276, | |
| "grad_norm": 4.9460978507995605, | |
| "learning_rate": 2.5715485647942526e-05, | |
| "loss": 1.2251, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 1.4482758620689655, | |
| "grad_norm": 8.297338485717773, | |
| "learning_rate": 2.566723296985009e-05, | |
| "loss": 1.244, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.4551724137931035, | |
| "grad_norm": 5.6764326095581055, | |
| "learning_rate": 2.561875591926061e-05, | |
| "loss": 2.075, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 1.4620689655172414, | |
| "grad_norm": 7.905850410461426, | |
| "learning_rate": 2.55700555158309e-05, | |
| "loss": 1.1372, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 1.4689655172413794, | |
| "grad_norm": 7.2166523933410645, | |
| "learning_rate": 2.552113278391575e-05, | |
| "loss": 0.8753, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 1.4758620689655173, | |
| "grad_norm": 16.44755744934082, | |
| "learning_rate": 2.5471988752546358e-05, | |
| "loss": 1.3347, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 1.4827586206896552, | |
| "grad_norm": 6.070692539215088, | |
| "learning_rate": 2.542262445540869e-05, | |
| "loss": 1.7499, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 1.489655172413793, | |
| "grad_norm": 7.000082492828369, | |
| "learning_rate": 2.5373040930821747e-05, | |
| "loss": 2.1478, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 1.4965517241379311, | |
| "grad_norm": 7.349568843841553, | |
| "learning_rate": 2.5323239221715704e-05, | |
| "loss": 1.4035, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 1.5034482758620689, | |
| "grad_norm": 6.242449760437012, | |
| "learning_rate": 2.5273220375609993e-05, | |
| "loss": 1.4238, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 1.510344827586207, | |
| "grad_norm": 5.620000839233398, | |
| "learning_rate": 2.5222985444591268e-05, | |
| "loss": 1.3079, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 1.5172413793103448, | |
| "grad_norm": 4.874967098236084, | |
| "learning_rate": 2.5172535485291263e-05, | |
| "loss": 0.5889, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.524137931034483, | |
| "grad_norm": 13.453874588012695, | |
| "learning_rate": 2.5121871558864588e-05, | |
| "loss": 3.2711, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 1.5310344827586206, | |
| "grad_norm": 24.48921775817871, | |
| "learning_rate": 2.5070994730966375e-05, | |
| "loss": 2.8233, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 1.5310344827586206, | |
| "eval_loss": 1.8946478366851807, | |
| "eval_runtime": 4.54, | |
| "eval_samples_per_second": 1.762, | |
| "eval_steps_per_second": 1.762, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 1.5379310344827586, | |
| "grad_norm": 4.243319034576416, | |
| "learning_rate": 2.5019906071729905e-05, | |
| "loss": 0.4053, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 1.5448275862068965, | |
| "grad_norm": 9.057891845703125, | |
| "learning_rate": 2.496860665574406e-05, | |
| "loss": 2.5334, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 1.5517241379310345, | |
| "grad_norm": 8.277237892150879, | |
| "learning_rate": 2.4917097562030756e-05, | |
| "loss": 2.1032, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.5586206896551724, | |
| "grad_norm": 4.527651786804199, | |
| "learning_rate": 2.4865379874022212e-05, | |
| "loss": 0.6529, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 1.5655172413793104, | |
| "grad_norm": 4.352250099182129, | |
| "learning_rate": 2.4813454679538192e-05, | |
| "loss": 0.2521, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 1.5724137931034483, | |
| "grad_norm": 5.923490524291992, | |
| "learning_rate": 2.4761323070763103e-05, | |
| "loss": 1.8706, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 1.5793103448275863, | |
| "grad_norm": 6.146652698516846, | |
| "learning_rate": 2.4708986144223038e-05, | |
| "loss": 1.4523, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 1.5862068965517242, | |
| "grad_norm": 8.59493350982666, | |
| "learning_rate": 2.4656445000762695e-05, | |
| "loss": 2.0485, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.593103448275862, | |
| "grad_norm": 14.89201545715332, | |
| "learning_rate": 2.4603700745522238e-05, | |
| "loss": 1.6968, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 7.599427700042725, | |
| "learning_rate": 2.455075448791403e-05, | |
| "loss": 0.5584, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 1.6068965517241378, | |
| "grad_norm": 6.137027263641357, | |
| "learning_rate": 2.4497607341599338e-05, | |
| "loss": 1.2578, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 1.613793103448276, | |
| "grad_norm": 13.683157920837402, | |
| "learning_rate": 2.444426042446486e-05, | |
| "loss": 0.3959, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 1.6206896551724137, | |
| "grad_norm": 6.342459201812744, | |
| "learning_rate": 2.439071485859924e-05, | |
| "loss": 1.5216, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 1.6275862068965519, | |
| "grad_norm": 4.803065776824951, | |
| "learning_rate": 2.433697177026947e-05, | |
| "loss": 1.2224, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 1.6344827586206896, | |
| "grad_norm": 19.011320114135742, | |
| "learning_rate": 2.4283032289897184e-05, | |
| "loss": 2.417, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 1.6413793103448275, | |
| "grad_norm": 13.680153846740723, | |
| "learning_rate": 2.4228897552034885e-05, | |
| "loss": 1.0688, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 1.6482758620689655, | |
| "grad_norm": 5.316374778747559, | |
| "learning_rate": 2.417456869534209e-05, | |
| "loss": 1.804, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 1.6551724137931034, | |
| "grad_norm": 4.965254783630371, | |
| "learning_rate": 2.4120046862561367e-05, | |
| "loss": 1.0666, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.6620689655172414, | |
| "grad_norm": 5.786849498748779, | |
| "learning_rate": 2.406533320049431e-05, | |
| "loss": 1.4944, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 1.6689655172413793, | |
| "grad_norm": 6.54045295715332, | |
| "learning_rate": 2.4010428859977416e-05, | |
| "loss": 0.9506, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 1.6758620689655173, | |
| "grad_norm": 8.71989631652832, | |
| "learning_rate": 2.3955334995857866e-05, | |
| "loss": 1.8664, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 1.6827586206896552, | |
| "grad_norm": 7.771244525909424, | |
| "learning_rate": 2.3900052766969252e-05, | |
| "loss": 2.7829, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 1.6896551724137931, | |
| "grad_norm": 13.747180938720703, | |
| "learning_rate": 2.3844583336107192e-05, | |
| "loss": 0.6658, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 1.6965517241379309, | |
| "grad_norm": 8.790626525878906, | |
| "learning_rate": 2.378892787000487e-05, | |
| "loss": 1.6198, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 1.703448275862069, | |
| "grad_norm": 6.457479000091553, | |
| "learning_rate": 2.37330875393085e-05, | |
| "loss": 2.0938, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 1.7103448275862068, | |
| "grad_norm": 3.5511231422424316, | |
| "learning_rate": 2.3677063518552706e-05, | |
| "loss": 1.3691, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 1.717241379310345, | |
| "grad_norm": 4.779417037963867, | |
| "learning_rate": 2.3620856986135807e-05, | |
| "loss": 1.4682, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 1.7241379310344827, | |
| "grad_norm": 10.626018524169922, | |
| "learning_rate": 2.356446912429504e-05, | |
| "loss": 1.7604, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.7310344827586208, | |
| "grad_norm": 9.10898208618164, | |
| "learning_rate": 2.3507901119081694e-05, | |
| "loss": 0.4235, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 1.7379310344827585, | |
| "grad_norm": 6.013878345489502, | |
| "learning_rate": 2.3451154160336145e-05, | |
| "loss": 1.2361, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 1.7448275862068967, | |
| "grad_norm": 6.5278401374816895, | |
| "learning_rate": 2.3394229441662863e-05, | |
| "loss": 2.053, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 1.7517241379310344, | |
| "grad_norm": 6.2794623374938965, | |
| "learning_rate": 2.3337128160405262e-05, | |
| "loss": 0.772, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 1.7586206896551724, | |
| "grad_norm": 7.884958744049072, | |
| "learning_rate": 2.3279851517620567e-05, | |
| "loss": 1.3663, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 1.7655172413793103, | |
| "grad_norm": 6.92486047744751, | |
| "learning_rate": 2.322240071805449e-05, | |
| "loss": 1.3793, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 1.7724137931034483, | |
| "grad_norm": 6.688532829284668, | |
| "learning_rate": 2.3164776970115952e-05, | |
| "loss": 2.1226, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 1.7793103448275862, | |
| "grad_norm": 5.486979007720947, | |
| "learning_rate": 2.310698148585162e-05, | |
| "loss": 1.8741, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 1.7862068965517242, | |
| "grad_norm": 4.790956497192383, | |
| "learning_rate": 2.3049015480920432e-05, | |
| "loss": 1.1631, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 1.7862068965517242, | |
| "eval_loss": 1.9128004312515259, | |
| "eval_runtime": 4.4978, | |
| "eval_samples_per_second": 1.779, | |
| "eval_steps_per_second": 1.779, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 1.793103448275862, | |
| "grad_norm": 7.004488945007324, | |
| "learning_rate": 2.299088017456803e-05, | |
| "loss": 1.5968, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": 9.21987533569336, | |
| "learning_rate": 2.29325767896011e-05, | |
| "loss": 1.7426, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 1.806896551724138, | |
| "grad_norm": 7.149972915649414, | |
| "learning_rate": 2.2874106552361672e-05, | |
| "loss": 1.2684, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 1.8137931034482757, | |
| "grad_norm": 4.868863105773926, | |
| "learning_rate": 2.2815470692701305e-05, | |
| "loss": 0.6387, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 1.8206896551724139, | |
| "grad_norm": 7.658527851104736, | |
| "learning_rate": 2.2756670443955236e-05, | |
| "loss": 1.2035, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 1.8275862068965516, | |
| "grad_norm": 4.457070827484131, | |
| "learning_rate": 2.2697707042916415e-05, | |
| "loss": 1.492, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 1.8344827586206898, | |
| "grad_norm": 3.999518394470215, | |
| "learning_rate": 2.2638581729809522e-05, | |
| "loss": 0.3712, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 1.8413793103448275, | |
| "grad_norm": 5.254199504852295, | |
| "learning_rate": 2.2579295748264856e-05, | |
| "loss": 1.5827, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 1.8482758620689657, | |
| "grad_norm": 11.072293281555176, | |
| "learning_rate": 2.2519850345292192e-05, | |
| "loss": 1.5692, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 1.8551724137931034, | |
| "grad_norm": 9.097825050354004, | |
| "learning_rate": 2.2460246771254525e-05, | |
| "loss": 2.0791, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 1.8620689655172413, | |
| "grad_norm": 15.463027954101562, | |
| "learning_rate": 2.2400486279841812e-05, | |
| "loss": 2.0508, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.8689655172413793, | |
| "grad_norm": 8.5389404296875, | |
| "learning_rate": 2.2340570128044567e-05, | |
| "loss": 0.9089, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 1.8758620689655172, | |
| "grad_norm": 7.47584867477417, | |
| "learning_rate": 2.228049957612744e-05, | |
| "loss": 1.6641, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 1.8827586206896552, | |
| "grad_norm": 5.4179253578186035, | |
| "learning_rate": 2.2220275887602688e-05, | |
| "loss": 1.9974, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 1.889655172413793, | |
| "grad_norm": 20.747957229614258, | |
| "learning_rate": 2.2159900329203642e-05, | |
| "loss": 3.0228, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 1.896551724137931, | |
| "grad_norm": 8.873815536499023, | |
| "learning_rate": 2.2099374170858004e-05, | |
| "loss": 1.7806, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.903448275862069, | |
| "grad_norm": 5.834484100341797, | |
| "learning_rate": 2.2038698685661188e-05, | |
| "loss": 1.2638, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 1.910344827586207, | |
| "grad_norm": 5.626514911651611, | |
| "learning_rate": 2.197787514984951e-05, | |
| "loss": 1.2453, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 1.9172413793103447, | |
| "grad_norm": 5.62680196762085, | |
| "learning_rate": 2.1916904842773355e-05, | |
| "loss": 1.6145, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 1.9241379310344828, | |
| "grad_norm": 10.727760314941406, | |
| "learning_rate": 2.1855789046870265e-05, | |
| "loss": 0.7303, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 1.9310344827586206, | |
| "grad_norm": 4.86237907409668, | |
| "learning_rate": 2.1794529047637962e-05, | |
| "loss": 0.8277, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.9379310344827587, | |
| "grad_norm": 5.81272554397583, | |
| "learning_rate": 2.1733126133607333e-05, | |
| "loss": 1.3026, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 1.9448275862068964, | |
| "grad_norm": 7.906366348266602, | |
| "learning_rate": 2.1671581596315277e-05, | |
| "loss": 1.6814, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 1.9517241379310346, | |
| "grad_norm": 4.704112529754639, | |
| "learning_rate": 2.160989673027759e-05, | |
| "loss": 0.6912, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 1.9586206896551723, | |
| "grad_norm": 4.953239440917969, | |
| "learning_rate": 2.154807283296171e-05, | |
| "loss": 0.1418, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 1.9655172413793105, | |
| "grad_norm": 5.499814033508301, | |
| "learning_rate": 2.1486111204759425e-05, | |
| "loss": 1.0075, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 1.9724137931034482, | |
| "grad_norm": 5.502691268920898, | |
| "learning_rate": 2.1424013148959535e-05, | |
| "loss": 1.6252, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 1.9793103448275862, | |
| "grad_norm": 9.957716941833496, | |
| "learning_rate": 2.1361779971720438e-05, | |
| "loss": 1.0677, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 1.986206896551724, | |
| "grad_norm": 4.3258280754089355, | |
| "learning_rate": 2.129941298204263e-05, | |
| "loss": 1.0192, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 1.993103448275862, | |
| "grad_norm": 7.173874855041504, | |
| "learning_rate": 2.1236913491741212e-05, | |
| "loss": 0.1295, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 5.360743045806885, | |
| "learning_rate": 2.117428281541827e-05, | |
| "loss": 0.8945, | |
| "step": 290 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 725, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 145, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.4562668925845504e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |