| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.081841432225064, | |
| "eval_steps": 500, | |
| "global_step": 400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.010230179028132993, | |
| "grad_norm": 3.7339282035827637, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 1.6402, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.020460358056265986, | |
| "grad_norm": 3.856332540512085, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 1.685, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.030690537084398978, | |
| "grad_norm": 3.6486527919769287, | |
| "learning_rate": 1.2e-05, | |
| "loss": 1.6308, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04092071611253197, | |
| "grad_norm": 3.6288094520568848, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 1.6336, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05115089514066496, | |
| "grad_norm": 3.33920955657959, | |
| "learning_rate": 2e-05, | |
| "loss": 1.5891, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.061381074168797956, | |
| "grad_norm": 2.808194160461426, | |
| "learning_rate": 1.9999996908023674e-05, | |
| "loss": 1.5542, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07161125319693094, | |
| "grad_norm": 2.197322368621826, | |
| "learning_rate": 1.9999987632096612e-05, | |
| "loss": 1.4569, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.08184143222506395, | |
| "grad_norm": 1.646809458732605, | |
| "learning_rate": 1.999997217222454e-05, | |
| "loss": 1.4049, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.09207161125319693, | |
| "grad_norm": 1.207854151725769, | |
| "learning_rate": 1.9999950528417027e-05, | |
| "loss": 1.3218, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.10230179028132992, | |
| "grad_norm": 0.9744110107421875, | |
| "learning_rate": 1.9999922700687455e-05, | |
| "loss": 1.3043, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11253196930946291, | |
| "grad_norm": 0.8862619996070862, | |
| "learning_rate": 1.999988868905303e-05, | |
| "loss": 1.2692, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.12276214833759591, | |
| "grad_norm": 0.808510422706604, | |
| "learning_rate": 1.999984849353479e-05, | |
| "loss": 1.241, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1329923273657289, | |
| "grad_norm": 0.7722910046577454, | |
| "learning_rate": 1.999980211415759e-05, | |
| "loss": 1.2167, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1432225063938619, | |
| "grad_norm": 0.735596239566803, | |
| "learning_rate": 1.9999749550950106e-05, | |
| "loss": 1.1848, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.1534526854219949, | |
| "grad_norm": 0.7540133595466614, | |
| "learning_rate": 1.9999690803944852e-05, | |
| "loss": 1.1839, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1636828644501279, | |
| "grad_norm": 0.7589508295059204, | |
| "learning_rate": 1.9999625873178146e-05, | |
| "loss": 1.1676, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.17391304347826086, | |
| "grad_norm": 0.7847907543182373, | |
| "learning_rate": 1.999955475869015e-05, | |
| "loss": 1.1459, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.18414322250639387, | |
| "grad_norm": 0.7236718535423279, | |
| "learning_rate": 1.9999477460524835e-05, | |
| "loss": 1.1253, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.19437340153452684, | |
| "grad_norm": 0.7120142579078674, | |
| "learning_rate": 1.9999393978730004e-05, | |
| "loss": 1.1217, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.20460358056265984, | |
| "grad_norm": 0.640995442867279, | |
| "learning_rate": 1.9999304313357282e-05, | |
| "loss": 1.112, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.21483375959079284, | |
| "grad_norm": 0.5680305361747742, | |
| "learning_rate": 1.9999208464462116e-05, | |
| "loss": 1.0985, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.22506393861892582, | |
| "grad_norm": 0.5688360929489136, | |
| "learning_rate": 1.9999106432103785e-05, | |
| "loss": 1.0823, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.23529411764705882, | |
| "grad_norm": 0.5916054844856262, | |
| "learning_rate": 1.9998998216345375e-05, | |
| "loss": 1.0523, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.24552429667519182, | |
| "grad_norm": 0.6135437488555908, | |
| "learning_rate": 1.9998883817253813e-05, | |
| "loss": 1.0757, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2557544757033248, | |
| "grad_norm": 0.587724506855011, | |
| "learning_rate": 1.999876323489984e-05, | |
| "loss": 1.0411, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2659846547314578, | |
| "grad_norm": 0.561601459980011, | |
| "learning_rate": 1.9998636469358023e-05, | |
| "loss": 1.0481, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.27621483375959077, | |
| "grad_norm": 0.48791056871414185, | |
| "learning_rate": 1.999850352070676e-05, | |
| "loss": 1.0061, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.2864450127877238, | |
| "grad_norm": 0.4305904507637024, | |
| "learning_rate": 1.9998364389028256e-05, | |
| "loss": 1.0076, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.2966751918158568, | |
| "grad_norm": 0.36149221658706665, | |
| "learning_rate": 1.9998219074408554e-05, | |
| "loss": 1.0093, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.3069053708439898, | |
| "grad_norm": 0.34878969192504883, | |
| "learning_rate": 1.999806757693752e-05, | |
| "loss": 0.9997, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3171355498721228, | |
| "grad_norm": 0.35569989681243896, | |
| "learning_rate": 1.9997909896708833e-05, | |
| "loss": 0.9904, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.3273657289002558, | |
| "grad_norm": 0.37640881538391113, | |
| "learning_rate": 1.9997746033820005e-05, | |
| "loss": 0.9959, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.3375959079283887, | |
| "grad_norm": 0.37813887000083923, | |
| "learning_rate": 1.9997575988372366e-05, | |
| "loss": 0.9708, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.34782608695652173, | |
| "grad_norm": 0.3413299322128296, | |
| "learning_rate": 1.9997399760471072e-05, | |
| "loss": 0.9689, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.35805626598465473, | |
| "grad_norm": 0.30490338802337646, | |
| "learning_rate": 1.9997217350225103e-05, | |
| "loss": 0.9774, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.36828644501278773, | |
| "grad_norm": 0.27457210421562195, | |
| "learning_rate": 1.999702875774726e-05, | |
| "loss": 0.9989, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.37851662404092073, | |
| "grad_norm": 0.26494237780570984, | |
| "learning_rate": 1.9996833983154166e-05, | |
| "loss": 0.9607, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.3887468030690537, | |
| "grad_norm": 0.2736992835998535, | |
| "learning_rate": 1.9996633026566265e-05, | |
| "loss": 0.956, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.3989769820971867, | |
| "grad_norm": 0.2966112494468689, | |
| "learning_rate": 1.999642588810784e-05, | |
| "loss": 0.9397, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.4092071611253197, | |
| "grad_norm": 0.304120272397995, | |
| "learning_rate": 1.999621256790697e-05, | |
| "loss": 0.9692, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4194373401534527, | |
| "grad_norm": 0.3025428354740143, | |
| "learning_rate": 1.9995993066095584e-05, | |
| "loss": 0.9315, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.4296675191815857, | |
| "grad_norm": 0.2758133113384247, | |
| "learning_rate": 1.9995767382809414e-05, | |
| "loss": 0.925, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.4398976982097187, | |
| "grad_norm": 0.26389235258102417, | |
| "learning_rate": 1.999553551818802e-05, | |
| "loss": 0.926, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.45012787723785164, | |
| "grad_norm": 0.24357713758945465, | |
| "learning_rate": 1.999529747237479e-05, | |
| "loss": 0.9375, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.46035805626598464, | |
| "grad_norm": 0.2292446494102478, | |
| "learning_rate": 1.9995053245516927e-05, | |
| "loss": 0.9425, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.47058823529411764, | |
| "grad_norm": 0.215789332985878, | |
| "learning_rate": 1.9994802837765464e-05, | |
| "loss": 0.9264, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.48081841432225064, | |
| "grad_norm": 0.2154732346534729, | |
| "learning_rate": 1.999454624927525e-05, | |
| "loss": 0.9284, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.49104859335038364, | |
| "grad_norm": 0.2164417803287506, | |
| "learning_rate": 1.9994283480204956e-05, | |
| "loss": 0.9339, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.5012787723785166, | |
| "grad_norm": 0.21539105474948883, | |
| "learning_rate": 1.9994014530717082e-05, | |
| "loss": 0.9049, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.5115089514066496, | |
| "grad_norm": 0.21105124056339264, | |
| "learning_rate": 1.9993739400977938e-05, | |
| "loss": 0.9105, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5217391304347826, | |
| "grad_norm": 0.21185389161109924, | |
| "learning_rate": 1.9993458091157668e-05, | |
| "loss": 0.927, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.5319693094629157, | |
| "grad_norm": 0.19724711775779724, | |
| "learning_rate": 1.9993170601430233e-05, | |
| "loss": 0.8957, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.5421994884910486, | |
| "grad_norm": 0.1938239187002182, | |
| "learning_rate": 1.999287693197341e-05, | |
| "loss": 0.9174, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.5524296675191815, | |
| "grad_norm": 0.19070130586624146, | |
| "learning_rate": 1.9992577082968808e-05, | |
| "loss": 0.9111, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.5626598465473146, | |
| "grad_norm": 0.1937451958656311, | |
| "learning_rate": 1.999227105460185e-05, | |
| "loss": 0.8977, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.5728900255754475, | |
| "grad_norm": 0.19541557133197784, | |
| "learning_rate": 1.9991958847061786e-05, | |
| "loss": 0.8845, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.5831202046035806, | |
| "grad_norm": 0.18689967691898346, | |
| "learning_rate": 1.999164046054168e-05, | |
| "loss": 0.8851, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.5933503836317136, | |
| "grad_norm": 0.18149493634700775, | |
| "learning_rate": 1.999131589523842e-05, | |
| "loss": 0.8919, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.6035805626598465, | |
| "grad_norm": 0.18779127299785614, | |
| "learning_rate": 1.999098515135272e-05, | |
| "loss": 0.898, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.6138107416879796, | |
| "grad_norm": 0.17797918617725372, | |
| "learning_rate": 1.9990648229089106e-05, | |
| "loss": 0.9014, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.6240409207161125, | |
| "grad_norm": 0.1641537845134735, | |
| "learning_rate": 1.999030512865593e-05, | |
| "loss": 0.8879, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.6342710997442456, | |
| "grad_norm": 0.18192438781261444, | |
| "learning_rate": 1.9989955850265364e-05, | |
| "loss": 0.8735, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.6445012787723785, | |
| "grad_norm": 0.17269515991210938, | |
| "learning_rate": 1.99896003941334e-05, | |
| "loss": 0.8808, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.6547314578005116, | |
| "grad_norm": 0.17067378759384155, | |
| "learning_rate": 1.9989238760479853e-05, | |
| "loss": 0.8803, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.6649616368286445, | |
| "grad_norm": 0.1700741946697235, | |
| "learning_rate": 1.9988870949528358e-05, | |
| "loss": 0.8805, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.6751918158567775, | |
| "grad_norm": 0.16453766822814941, | |
| "learning_rate": 1.9988496961506356e-05, | |
| "loss": 0.8854, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.6854219948849105, | |
| "grad_norm": 0.21169471740722656, | |
| "learning_rate": 1.998811679664513e-05, | |
| "loss": 0.8772, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.6956521739130435, | |
| "grad_norm": 0.17419219017028809, | |
| "learning_rate": 1.998773045517977e-05, | |
| "loss": 0.8685, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.7058823529411765, | |
| "grad_norm": 0.1648634821176529, | |
| "learning_rate": 1.998733793734918e-05, | |
| "loss": 0.8547, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.7161125319693095, | |
| "grad_norm": 0.1565054953098297, | |
| "learning_rate": 1.9986939243396103e-05, | |
| "loss": 0.8598, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.7263427109974424, | |
| "grad_norm": 0.1954575926065445, | |
| "learning_rate": 1.9986534373567085e-05, | |
| "loss": 0.8602, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.7365728900255755, | |
| "grad_norm": 0.16202539205551147, | |
| "learning_rate": 1.998612332811249e-05, | |
| "loss": 0.8603, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.7468030690537084, | |
| "grad_norm": 0.16558033227920532, | |
| "learning_rate": 1.9985706107286515e-05, | |
| "loss": 0.8624, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.7570332480818415, | |
| "grad_norm": 0.16333763301372528, | |
| "learning_rate": 1.9985282711347164e-05, | |
| "loss": 0.8882, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.7672634271099744, | |
| "grad_norm": 0.1662484109401703, | |
| "learning_rate": 1.9984853140556258e-05, | |
| "loss": 0.8548, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.7774936061381074, | |
| "grad_norm": 0.15836550295352936, | |
| "learning_rate": 1.998441739517945e-05, | |
| "loss": 0.8556, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.7877237851662404, | |
| "grad_norm": 0.15881623327732086, | |
| "learning_rate": 1.99839754754862e-05, | |
| "loss": 0.8519, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.7979539641943734, | |
| "grad_norm": 0.1609843522310257, | |
| "learning_rate": 1.9983527381749787e-05, | |
| "loss": 0.8566, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.8081841432225064, | |
| "grad_norm": 0.15333859622478485, | |
| "learning_rate": 1.998307311424731e-05, | |
| "loss": 0.847, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.8184143222506394, | |
| "grad_norm": 0.15633417665958405, | |
| "learning_rate": 1.9982612673259686e-05, | |
| "loss": 0.8644, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.8286445012787724, | |
| "grad_norm": 0.16742706298828125, | |
| "learning_rate": 1.9982146059071653e-05, | |
| "loss": 0.8628, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.8388746803069054, | |
| "grad_norm": 0.160526841878891, | |
| "learning_rate": 1.9981673271971757e-05, | |
| "loss": 0.8198, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.8491048593350383, | |
| "grad_norm": 0.1579267680644989, | |
| "learning_rate": 1.9981194312252375e-05, | |
| "loss": 0.8582, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.8593350383631714, | |
| "grad_norm": 0.15127578377723694, | |
| "learning_rate": 1.9980709180209686e-05, | |
| "loss": 0.8562, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.8695652173913043, | |
| "grad_norm": 0.1515190452337265, | |
| "learning_rate": 1.99802178761437e-05, | |
| "loss": 0.8541, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.8797953964194374, | |
| "grad_norm": 0.1643359363079071, | |
| "learning_rate": 1.9979720400358233e-05, | |
| "loss": 0.8782, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.8900255754475703, | |
| "grad_norm": 0.17986010015010834, | |
| "learning_rate": 1.9979216753160918e-05, | |
| "loss": 0.8377, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.9002557544757033, | |
| "grad_norm": 0.1635770946741104, | |
| "learning_rate": 1.9978706934863215e-05, | |
| "loss": 0.8508, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.9104859335038363, | |
| "grad_norm": 0.15602238476276398, | |
| "learning_rate": 1.9978190945780394e-05, | |
| "loss": 0.8412, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.9207161125319693, | |
| "grad_norm": 0.15934546291828156, | |
| "learning_rate": 1.9977668786231536e-05, | |
| "loss": 0.8255, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.9309462915601023, | |
| "grad_norm": 0.15885022282600403, | |
| "learning_rate": 1.997714045653954e-05, | |
| "loss": 0.8492, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.9411764705882353, | |
| "grad_norm": 0.16822269558906555, | |
| "learning_rate": 1.9976605957031124e-05, | |
| "loss": 0.8354, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.9514066496163683, | |
| "grad_norm": 0.1673271358013153, | |
| "learning_rate": 1.9976065288036824e-05, | |
| "loss": 0.8294, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.9616368286445013, | |
| "grad_norm": 0.15639379620552063, | |
| "learning_rate": 1.9975518449890984e-05, | |
| "loss": 0.8586, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.9718670076726342, | |
| "grad_norm": 0.16323138773441315, | |
| "learning_rate": 1.997496544293177e-05, | |
| "loss": 0.8451, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.9820971867007673, | |
| "grad_norm": 0.15901896357536316, | |
| "learning_rate": 1.9974406267501153e-05, | |
| "loss": 0.8409, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.9923273657289002, | |
| "grad_norm": 0.15179632604122162, | |
| "learning_rate": 1.9973840923944926e-05, | |
| "loss": 0.8358, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.19052907824516296, | |
| "learning_rate": 1.9973269412612696e-05, | |
| "loss": 0.8236, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.010230179028133, | |
| "grad_norm": 0.16732874512672424, | |
| "learning_rate": 1.997269173385788e-05, | |
| "loss": 0.8225, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 1.020460358056266, | |
| "grad_norm": 0.17052046954631805, | |
| "learning_rate": 1.9972107888037718e-05, | |
| "loss": 0.8249, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.030690537084399, | |
| "grad_norm": 0.16232553124427795, | |
| "learning_rate": 1.9971517875513254e-05, | |
| "loss": 0.8347, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 1.040920716112532, | |
| "grad_norm": 0.17455045878887177, | |
| "learning_rate": 1.997092169664935e-05, | |
| "loss": 0.8411, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.051150895140665, | |
| "grad_norm": 0.1684006005525589, | |
| "learning_rate": 1.9970319351814677e-05, | |
| "loss": 0.8197, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 1.061381074168798, | |
| "grad_norm": 0.17193110287189484, | |
| "learning_rate": 1.9969710841381723e-05, | |
| "loss": 0.8164, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.0716112531969308, | |
| "grad_norm": 0.18234021961688995, | |
| "learning_rate": 1.9969096165726794e-05, | |
| "loss": 0.819, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.081841432225064, | |
| "grad_norm": 0.1758105605840683, | |
| "learning_rate": 1.9968475325229995e-05, | |
| "loss": 0.8101, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.092071611253197, | |
| "grad_norm": 0.16415317356586456, | |
| "learning_rate": 1.9967848320275253e-05, | |
| "loss": 0.8394, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 1.10230179028133, | |
| "grad_norm": 0.16018615663051605, | |
| "learning_rate": 1.9967215151250305e-05, | |
| "loss": 0.8166, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.1125319693094629, | |
| "grad_norm": 0.1779460608959198, | |
| "learning_rate": 1.9966575818546702e-05, | |
| "loss": 0.8286, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 1.1227621483375958, | |
| "grad_norm": 0.1844969242811203, | |
| "learning_rate": 1.9965930322559803e-05, | |
| "loss": 0.8079, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.132992327365729, | |
| "grad_norm": 0.17768210172653198, | |
| "learning_rate": 1.9965278663688776e-05, | |
| "loss": 0.8237, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 1.143222506393862, | |
| "grad_norm": 0.17491723597049713, | |
| "learning_rate": 1.996462084233661e-05, | |
| "loss": 0.825, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.1534526854219949, | |
| "grad_norm": 0.17149733006954193, | |
| "learning_rate": 1.9963956858910098e-05, | |
| "loss": 0.8289, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 1.1636828644501278, | |
| "grad_norm": 0.16866537928581238, | |
| "learning_rate": 1.9963286713819836e-05, | |
| "loss": 0.8151, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.1739130434782608, | |
| "grad_norm": 0.1781005710363388, | |
| "learning_rate": 1.9962610407480248e-05, | |
| "loss": 0.8223, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.184143222506394, | |
| "grad_norm": 0.17955420911312103, | |
| "learning_rate": 1.996192794030955e-05, | |
| "loss": 0.8317, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.1943734015345269, | |
| "grad_norm": 0.1959114521741867, | |
| "learning_rate": 1.9961239312729787e-05, | |
| "loss": 0.7925, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.2046035805626598, | |
| "grad_norm": 0.18740878999233246, | |
| "learning_rate": 1.9960544525166794e-05, | |
| "loss": 0.8141, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.2148337595907928, | |
| "grad_norm": 0.17671266198158264, | |
| "learning_rate": 1.995984357805023e-05, | |
| "loss": 0.824, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 1.2250639386189257, | |
| "grad_norm": 0.1796875149011612, | |
| "learning_rate": 1.9959136471813556e-05, | |
| "loss": 0.7951, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.2352941176470589, | |
| "grad_norm": 0.17882168292999268, | |
| "learning_rate": 1.9958423206894043e-05, | |
| "loss": 0.8056, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 1.2455242966751918, | |
| "grad_norm": 0.18344885110855103, | |
| "learning_rate": 1.9957703783732768e-05, | |
| "loss": 0.807, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 1.2557544757033248, | |
| "grad_norm": 0.19720099866390228, | |
| "learning_rate": 1.995697820277462e-05, | |
| "loss": 0.8006, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 1.265984654731458, | |
| "grad_norm": 0.18990914523601532, | |
| "learning_rate": 1.9956246464468294e-05, | |
| "loss": 0.7878, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 1.2762148337595907, | |
| "grad_norm": 0.1771262288093567, | |
| "learning_rate": 1.99555085692663e-05, | |
| "loss": 0.8164, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.2864450127877238, | |
| "grad_norm": 0.1780935823917389, | |
| "learning_rate": 1.995476451762494e-05, | |
| "loss": 0.8013, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 1.2966751918158568, | |
| "grad_norm": 0.1821814477443695, | |
| "learning_rate": 1.995401431000434e-05, | |
| "loss": 0.8041, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 1.3069053708439897, | |
| "grad_norm": 0.18167997896671295, | |
| "learning_rate": 1.9953257946868418e-05, | |
| "loss": 0.7855, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 1.317135549872123, | |
| "grad_norm": 0.18690866231918335, | |
| "learning_rate": 1.995249542868491e-05, | |
| "loss": 0.7983, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 1.3273657289002558, | |
| "grad_norm": 0.2091519981622696, | |
| "learning_rate": 1.995172675592535e-05, | |
| "loss": 0.8237, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.3375959079283888, | |
| "grad_norm": 0.19291919469833374, | |
| "learning_rate": 1.9950951929065085e-05, | |
| "loss": 0.7869, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 1.3478260869565217, | |
| "grad_norm": 0.19281232357025146, | |
| "learning_rate": 1.9950170948583262e-05, | |
| "loss": 0.8145, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 1.3580562659846547, | |
| "grad_norm": 0.26430603861808777, | |
| "learning_rate": 1.994938381496284e-05, | |
| "loss": 0.7965, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 1.3682864450127878, | |
| "grad_norm": 0.19186891615390778, | |
| "learning_rate": 1.994859052869057e-05, | |
| "loss": 0.7961, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 1.3785166240409208, | |
| "grad_norm": 0.20330464839935303, | |
| "learning_rate": 1.9947791090257023e-05, | |
| "loss": 0.7844, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.3887468030690537, | |
| "grad_norm": 0.20833194255828857, | |
| "learning_rate": 1.9946985500156567e-05, | |
| "loss": 0.7757, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 1.3989769820971867, | |
| "grad_norm": 0.1985306292772293, | |
| "learning_rate": 1.9946173758887377e-05, | |
| "loss": 0.8061, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 1.4092071611253196, | |
| "grad_norm": 0.19251206517219543, | |
| "learning_rate": 1.9945355866951426e-05, | |
| "loss": 0.804, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 1.4194373401534528, | |
| "grad_norm": 0.2225429117679596, | |
| "learning_rate": 1.9944531824854497e-05, | |
| "loss": 0.787, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 1.4296675191815857, | |
| "grad_norm": 0.1990213543176651, | |
| "learning_rate": 1.994370163310617e-05, | |
| "loss": 0.8052, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.4398976982097187, | |
| "grad_norm": 0.20235106348991394, | |
| "learning_rate": 1.9942865292219837e-05, | |
| "loss": 0.8106, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 1.4501278772378516, | |
| "grad_norm": 0.20018866658210754, | |
| "learning_rate": 1.9942022802712684e-05, | |
| "loss": 0.8016, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 1.4603580562659846, | |
| "grad_norm": 0.2079232931137085, | |
| "learning_rate": 1.9941174165105702e-05, | |
| "loss": 0.788, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 1.4705882352941178, | |
| "grad_norm": 0.2163192331790924, | |
| "learning_rate": 1.994031937992369e-05, | |
| "loss": 0.7913, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 1.4808184143222507, | |
| "grad_norm": 0.20073741674423218, | |
| "learning_rate": 1.9939458447695235e-05, | |
| "loss": 0.7926, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.4910485933503836, | |
| "grad_norm": 0.20287558436393738, | |
| "learning_rate": 1.993859136895274e-05, | |
| "loss": 0.8034, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 1.5012787723785166, | |
| "grad_norm": 0.22918002307415009, | |
| "learning_rate": 1.9937718144232397e-05, | |
| "loss": 0.7924, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 1.5115089514066495, | |
| "grad_norm": 0.20228266716003418, | |
| "learning_rate": 1.9936838774074207e-05, | |
| "loss": 0.7944, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 1.5217391304347827, | |
| "grad_norm": 0.19842855632305145, | |
| "learning_rate": 1.993595325902197e-05, | |
| "loss": 0.8043, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 1.5319693094629157, | |
| "grad_norm": 0.22039633989334106, | |
| "learning_rate": 1.9935061599623278e-05, | |
| "loss": 0.7794, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.5421994884910486, | |
| "grad_norm": 0.2239089459180832, | |
| "learning_rate": 1.993416379642954e-05, | |
| "loss": 0.773, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 1.5524296675191815, | |
| "grad_norm": 0.2272518277168274, | |
| "learning_rate": 1.9933259849995942e-05, | |
| "loss": 0.7771, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 1.5626598465473145, | |
| "grad_norm": 0.20447060465812683, | |
| "learning_rate": 1.9932349760881483e-05, | |
| "loss": 0.8027, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 1.5728900255754477, | |
| "grad_norm": 0.20220829546451569, | |
| "learning_rate": 1.9931433529648964e-05, | |
| "loss": 0.7845, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 1.5831202046035806, | |
| "grad_norm": 0.2160012573003769, | |
| "learning_rate": 1.9930511156864974e-05, | |
| "loss": 0.7807, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.5933503836317136, | |
| "grad_norm": 0.2220025658607483, | |
| "learning_rate": 1.99295826430999e-05, | |
| "loss": 0.7759, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 1.6035805626598465, | |
| "grad_norm": 0.20744675397872925, | |
| "learning_rate": 1.9928647988927937e-05, | |
| "loss": 0.7777, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 1.6138107416879794, | |
| "grad_norm": 0.2259499430656433, | |
| "learning_rate": 1.9927707194927067e-05, | |
| "loss": 0.7817, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 1.6240409207161126, | |
| "grad_norm": 0.21047933399677277, | |
| "learning_rate": 1.992676026167907e-05, | |
| "loss": 0.7803, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 1.6342710997442456, | |
| "grad_norm": 0.24594929814338684, | |
| "learning_rate": 1.9925807189769533e-05, | |
| "loss": 0.7687, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.6445012787723785, | |
| "grad_norm": 0.22714115679264069, | |
| "learning_rate": 1.9924847979787826e-05, | |
| "loss": 0.7521, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 1.6547314578005117, | |
| "grad_norm": 0.21901191771030426, | |
| "learning_rate": 1.992388263232712e-05, | |
| "loss": 0.7751, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 1.6649616368286444, | |
| "grad_norm": 0.25662556290626526, | |
| "learning_rate": 1.992291114798438e-05, | |
| "loss": 0.7801, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 1.6751918158567776, | |
| "grad_norm": 0.2206140011548996, | |
| "learning_rate": 1.992193352736037e-05, | |
| "loss": 0.7943, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 1.6854219948849105, | |
| "grad_norm": 0.2689746916294098, | |
| "learning_rate": 1.9920949771059647e-05, | |
| "loss": 0.7697, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.6956521739130435, | |
| "grad_norm": 0.22856131196022034, | |
| "learning_rate": 1.9919959879690553e-05, | |
| "loss": 0.7596, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 1.7058823529411766, | |
| "grad_norm": 0.252189964056015, | |
| "learning_rate": 1.9918963853865243e-05, | |
| "loss": 0.7893, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 1.7161125319693094, | |
| "grad_norm": 0.22657926380634308, | |
| "learning_rate": 1.9917961694199653e-05, | |
| "loss": 0.7633, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 1.7263427109974425, | |
| "grad_norm": 0.20404541492462158, | |
| "learning_rate": 1.9916953401313505e-05, | |
| "loss": 0.7923, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 1.7365728900255755, | |
| "grad_norm": 0.3168542683124542, | |
| "learning_rate": 1.9915938975830332e-05, | |
| "loss": 0.7906, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.7468030690537084, | |
| "grad_norm": 0.2238597571849823, | |
| "learning_rate": 1.9914918418377444e-05, | |
| "loss": 0.7836, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 1.7570332480818416, | |
| "grad_norm": 0.23487034440040588, | |
| "learning_rate": 1.9913891729585955e-05, | |
| "loss": 0.7762, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 1.7672634271099743, | |
| "grad_norm": 0.24799533188343048, | |
| "learning_rate": 1.9912858910090758e-05, | |
| "loss": 0.7786, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 1.7774936061381075, | |
| "grad_norm": 0.2436627745628357, | |
| "learning_rate": 1.9911819960530548e-05, | |
| "loss": 0.7832, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 1.7877237851662404, | |
| "grad_norm": 0.25562822818756104, | |
| "learning_rate": 1.9910774881547803e-05, | |
| "loss": 0.771, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.7979539641943734, | |
| "grad_norm": 0.2377200573682785, | |
| "learning_rate": 1.9909723673788797e-05, | |
| "loss": 0.7614, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 1.8081841432225065, | |
| "grad_norm": 0.2661269009113312, | |
| "learning_rate": 1.9908666337903593e-05, | |
| "loss": 0.7688, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 1.8184143222506393, | |
| "grad_norm": 0.23161008954048157, | |
| "learning_rate": 1.9907602874546042e-05, | |
| "loss": 0.7792, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 1.8286445012787724, | |
| "grad_norm": 0.2372981458902359, | |
| "learning_rate": 1.990653328437378e-05, | |
| "loss": 0.7672, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 1.8388746803069054, | |
| "grad_norm": 0.24873419106006622, | |
| "learning_rate": 1.9905457568048243e-05, | |
| "loss": 0.769, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.8491048593350383, | |
| "grad_norm": 0.24799948930740356, | |
| "learning_rate": 1.9904375726234645e-05, | |
| "loss": 0.7794, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 1.8593350383631715, | |
| "grad_norm": 0.262285977602005, | |
| "learning_rate": 1.9903287759601994e-05, | |
| "loss": 0.7763, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 1.8695652173913042, | |
| "grad_norm": 0.2708827555179596, | |
| "learning_rate": 1.9902193668823085e-05, | |
| "loss": 0.7703, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 1.8797953964194374, | |
| "grad_norm": 0.25064393877983093, | |
| "learning_rate": 1.9901093454574494e-05, | |
| "loss": 0.7911, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 1.8900255754475703, | |
| "grad_norm": 0.25976258516311646, | |
| "learning_rate": 1.989998711753659e-05, | |
| "loss": 0.776, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.9002557544757033, | |
| "grad_norm": 0.26402992010116577, | |
| "learning_rate": 1.9898874658393525e-05, | |
| "loss": 0.792, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 1.9104859335038364, | |
| "grad_norm": 0.2455168217420578, | |
| "learning_rate": 1.9897756077833245e-05, | |
| "loss": 0.7744, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 1.9207161125319692, | |
| "grad_norm": 0.26314792037010193, | |
| "learning_rate": 1.9896631376547467e-05, | |
| "loss": 0.7683, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 1.9309462915601023, | |
| "grad_norm": 0.25260472297668457, | |
| "learning_rate": 1.9895500555231706e-05, | |
| "loss": 0.7905, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 1.9411764705882353, | |
| "grad_norm": 0.2529143989086151, | |
| "learning_rate": 1.9894363614585252e-05, | |
| "loss": 0.7773, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.9514066496163682, | |
| "grad_norm": 0.2417425513267517, | |
| "learning_rate": 1.989322055531119e-05, | |
| "loss": 0.7632, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 1.9616368286445014, | |
| "grad_norm": 0.2735307216644287, | |
| "learning_rate": 1.9892071378116378e-05, | |
| "loss": 0.7788, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 1.9718670076726341, | |
| "grad_norm": 0.2711434066295624, | |
| "learning_rate": 1.9890916083711463e-05, | |
| "loss": 0.7735, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 1.9820971867007673, | |
| "grad_norm": 0.24282266199588776, | |
| "learning_rate": 1.9889754672810872e-05, | |
| "loss": 0.759, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 1.9923273657289002, | |
| "grad_norm": 0.275905966758728, | |
| "learning_rate": 1.9888587146132817e-05, | |
| "loss": 0.8014, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.2884292006492615, | |
| "learning_rate": 1.9887413504399295e-05, | |
| "loss": 0.7734, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 2.010230179028133, | |
| "grad_norm": 0.28079572319984436, | |
| "learning_rate": 1.988623374833607e-05, | |
| "loss": 0.7619, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 2.020460358056266, | |
| "grad_norm": 0.25205302238464355, | |
| "learning_rate": 1.988504787867271e-05, | |
| "loss": 0.7549, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 2.030690537084399, | |
| "grad_norm": 0.2778927981853485, | |
| "learning_rate": 1.9883855896142547e-05, | |
| "loss": 0.7601, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 2.040920716112532, | |
| "grad_norm": 0.29224029183387756, | |
| "learning_rate": 1.988265780148269e-05, | |
| "loss": 0.7593, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.051150895140665, | |
| "grad_norm": 0.2718479037284851, | |
| "learning_rate": 1.9881453595434042e-05, | |
| "loss": 0.7704, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 2.061381074168798, | |
| "grad_norm": 0.2963065803050995, | |
| "learning_rate": 1.988024327874128e-05, | |
| "loss": 0.7756, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 2.071611253196931, | |
| "grad_norm": 0.29864153265953064, | |
| "learning_rate": 1.9879026852152857e-05, | |
| "loss": 0.7447, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 2.081841432225064, | |
| "grad_norm": 0.25865793228149414, | |
| "learning_rate": 1.9877804316421e-05, | |
| "loss": 0.7593, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 2.0920716112531967, | |
| "grad_norm": 0.33318352699279785, | |
| "learning_rate": 1.9876575672301726e-05, | |
| "loss": 0.755, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 2.10230179028133, | |
| "grad_norm": 0.2629791796207428, | |
| "learning_rate": 1.9875340920554816e-05, | |
| "loss": 0.7556, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 2.112531969309463, | |
| "grad_norm": 0.26791051030158997, | |
| "learning_rate": 1.9874100061943845e-05, | |
| "loss": 0.7565, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 2.122762148337596, | |
| "grad_norm": 0.32693561911582947, | |
| "learning_rate": 1.9872853097236142e-05, | |
| "loss": 0.7498, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 2.132992327365729, | |
| "grad_norm": 0.28684085607528687, | |
| "learning_rate": 1.987160002720283e-05, | |
| "loss": 0.7757, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 2.1432225063938617, | |
| "grad_norm": 0.3658446669578552, | |
| "learning_rate": 1.9870340852618802e-05, | |
| "loss": 0.7541, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.153452685421995, | |
| "grad_norm": 0.2634979784488678, | |
| "learning_rate": 1.9869075574262728e-05, | |
| "loss": 0.7626, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 2.163682864450128, | |
| "grad_norm": 0.2918095290660858, | |
| "learning_rate": 1.9867804192917043e-05, | |
| "loss": 0.7437, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 2.1739130434782608, | |
| "grad_norm": 0.3078654408454895, | |
| "learning_rate": 1.9866526709367967e-05, | |
| "loss": 0.7762, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 2.184143222506394, | |
| "grad_norm": 0.4585474133491516, | |
| "learning_rate": 1.9865243124405493e-05, | |
| "loss": 0.7744, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 2.1943734015345266, | |
| "grad_norm": 0.30667614936828613, | |
| "learning_rate": 1.986395343882338e-05, | |
| "loss": 0.7698, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 2.20460358056266, | |
| "grad_norm": 0.32421836256980896, | |
| "learning_rate": 1.986265765341916e-05, | |
| "loss": 0.7602, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 2.214833759590793, | |
| "grad_norm": 0.2798852324485779, | |
| "learning_rate": 1.986135576899415e-05, | |
| "loss": 0.7417, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 2.2250639386189257, | |
| "grad_norm": 0.28992176055908203, | |
| "learning_rate": 1.9860047786353426e-05, | |
| "loss": 0.7729, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 2.235294117647059, | |
| "grad_norm": 0.3212791085243225, | |
| "learning_rate": 1.985873370630583e-05, | |
| "loss": 0.759, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 2.2455242966751916, | |
| "grad_norm": 0.27983346581459045, | |
| "learning_rate": 1.9857413529663993e-05, | |
| "loss": 0.7648, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.2557544757033248, | |
| "grad_norm": 0.3009434640407562, | |
| "learning_rate": 1.98560872572443e-05, | |
| "loss": 0.7274, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 2.265984654731458, | |
| "grad_norm": 0.28235509991645813, | |
| "learning_rate": 1.9854754889866915e-05, | |
| "loss": 0.7667, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 2.2762148337595907, | |
| "grad_norm": 0.3221166729927063, | |
| "learning_rate": 1.9853416428355765e-05, | |
| "loss": 0.7402, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 2.286445012787724, | |
| "grad_norm": 0.27435916662216187, | |
| "learning_rate": 1.9852071873538553e-05, | |
| "loss": 0.749, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 2.296675191815857, | |
| "grad_norm": 0.27836698293685913, | |
| "learning_rate": 1.985072122624674e-05, | |
| "loss": 0.7444, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 2.3069053708439897, | |
| "grad_norm": 0.287270724773407, | |
| "learning_rate": 1.984936448731556e-05, | |
| "loss": 0.762, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 2.317135549872123, | |
| "grad_norm": 0.3191712200641632, | |
| "learning_rate": 1.9848001657584016e-05, | |
| "loss": 0.748, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 2.3273657289002556, | |
| "grad_norm": 0.2816384732723236, | |
| "learning_rate": 1.9846632737894878e-05, | |
| "loss": 0.7445, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 2.337595907928389, | |
| "grad_norm": 0.294630229473114, | |
| "learning_rate": 1.9845257729094672e-05, | |
| "loss": 0.7477, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 2.3478260869565215, | |
| "grad_norm": 0.2944187819957733, | |
| "learning_rate": 1.9843876632033707e-05, | |
| "loss": 0.7443, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.3580562659846547, | |
| "grad_norm": 0.26522430777549744, | |
| "learning_rate": 1.984248944756604e-05, | |
| "loss": 0.7632, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 2.368286445012788, | |
| "grad_norm": 0.33316174149513245, | |
| "learning_rate": 1.98410961765495e-05, | |
| "loss": 0.7519, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 2.3785166240409206, | |
| "grad_norm": 0.30234989523887634, | |
| "learning_rate": 1.983969681984568e-05, | |
| "loss": 0.7559, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 2.3887468030690537, | |
| "grad_norm": 0.31727346777915955, | |
| "learning_rate": 1.9838291378319935e-05, | |
| "loss": 0.7484, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 2.398976982097187, | |
| "grad_norm": 0.2959267497062683, | |
| "learning_rate": 1.9836879852841387e-05, | |
| "loss": 0.7378, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 2.4092071611253196, | |
| "grad_norm": 0.31137242913246155, | |
| "learning_rate": 1.9835462244282912e-05, | |
| "loss": 0.7481, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 2.419437340153453, | |
| "grad_norm": 0.3378095030784607, | |
| "learning_rate": 1.9834038553521155e-05, | |
| "loss": 0.7506, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 2.4296675191815855, | |
| "grad_norm": 0.2913769781589508, | |
| "learning_rate": 1.9832608781436516e-05, | |
| "loss": 0.7432, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 2.4398976982097187, | |
| "grad_norm": 0.4157828092575073, | |
| "learning_rate": 1.9831172928913163e-05, | |
| "loss": 0.7496, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 2.4501278772378514, | |
| "grad_norm": 0.3153923451900482, | |
| "learning_rate": 1.982973099683902e-05, | |
| "loss": 0.7611, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.4603580562659846, | |
| "grad_norm": 0.3100709915161133, | |
| "learning_rate": 1.9828282986105768e-05, | |
| "loss": 0.7417, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 2.4705882352941178, | |
| "grad_norm": 0.355727881193161, | |
| "learning_rate": 1.9826828897608855e-05, | |
| "loss": 0.7421, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 2.4808184143222505, | |
| "grad_norm": 0.31488820910453796, | |
| "learning_rate": 1.982536873224748e-05, | |
| "loss": 0.7603, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 2.4910485933503836, | |
| "grad_norm": 0.27576926350593567, | |
| "learning_rate": 1.9823902490924603e-05, | |
| "loss": 0.7527, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 2.501278772378517, | |
| "grad_norm": 0.3244059085845947, | |
| "learning_rate": 1.9822430174546938e-05, | |
| "loss": 0.7376, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 2.5115089514066495, | |
| "grad_norm": 0.3047364354133606, | |
| "learning_rate": 1.982095178402496e-05, | |
| "loss": 0.7534, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 2.5217391304347827, | |
| "grad_norm": 0.29374366998672485, | |
| "learning_rate": 1.9819467320272897e-05, | |
| "loss": 0.7414, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 2.531969309462916, | |
| "grad_norm": 0.3449955880641937, | |
| "learning_rate": 1.981797678420874e-05, | |
| "loss": 0.7369, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 2.5421994884910486, | |
| "grad_norm": 0.3467267155647278, | |
| "learning_rate": 1.9816480176754225e-05, | |
| "loss": 0.7434, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 2.5524296675191813, | |
| "grad_norm": 0.3496444821357727, | |
| "learning_rate": 1.981497749883485e-05, | |
| "loss": 0.7639, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.5626598465473145, | |
| "grad_norm": 0.29089784622192383, | |
| "learning_rate": 1.9813468751379856e-05, | |
| "loss": 0.7516, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 2.5728900255754477, | |
| "grad_norm": 0.3429134786128998, | |
| "learning_rate": 1.981195393532226e-05, | |
| "loss": 0.7476, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 2.5831202046035804, | |
| "grad_norm": 0.2926439642906189, | |
| "learning_rate": 1.9810433051598797e-05, | |
| "loss": 0.7456, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 2.5933503836317136, | |
| "grad_norm": 0.3356344401836395, | |
| "learning_rate": 1.980890610114999e-05, | |
| "loss": 0.7559, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 2.6035805626598467, | |
| "grad_norm": 0.34643828868865967, | |
| "learning_rate": 1.9807373084920093e-05, | |
| "loss": 0.7477, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 2.6138107416879794, | |
| "grad_norm": 0.2760990858078003, | |
| "learning_rate": 1.980583400385712e-05, | |
| "loss": 0.778, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 2.6240409207161126, | |
| "grad_norm": 0.38434210419654846, | |
| "learning_rate": 1.9804288858912825e-05, | |
| "loss": 0.7404, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 2.634271099744246, | |
| "grad_norm": 0.3008972406387329, | |
| "learning_rate": 1.9802737651042717e-05, | |
| "loss": 0.726, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 2.6445012787723785, | |
| "grad_norm": 0.30021610856056213, | |
| "learning_rate": 1.9801180381206065e-05, | |
| "loss": 0.7478, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 2.6547314578005117, | |
| "grad_norm": 0.35837844014167786, | |
| "learning_rate": 1.979961705036587e-05, | |
| "loss": 0.7503, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.6649616368286444, | |
| "grad_norm": 0.3149022161960602, | |
| "learning_rate": 1.979804765948889e-05, | |
| "loss": 0.7574, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 2.6751918158567776, | |
| "grad_norm": 0.35966795682907104, | |
| "learning_rate": 1.979647220954563e-05, | |
| "loss": 0.761, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 2.6854219948849103, | |
| "grad_norm": 0.3725556433200836, | |
| "learning_rate": 1.9794890701510337e-05, | |
| "loss": 0.7544, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 2.6956521739130435, | |
| "grad_norm": 0.30502018332481384, | |
| "learning_rate": 1.9793303136361016e-05, | |
| "loss": 0.74, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 2.7058823529411766, | |
| "grad_norm": 0.36470985412597656, | |
| "learning_rate": 1.97917095150794e-05, | |
| "loss": 0.7429, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 2.7161125319693094, | |
| "grad_norm": 0.3593257665634155, | |
| "learning_rate": 1.9790109838650987e-05, | |
| "loss": 0.7362, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 2.7263427109974425, | |
| "grad_norm": 0.3576882481575012, | |
| "learning_rate": 1.9788504108065002e-05, | |
| "loss": 0.7415, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 2.7365728900255757, | |
| "grad_norm": 0.48933324217796326, | |
| "learning_rate": 1.978689232431442e-05, | |
| "loss": 0.7347, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 2.7468030690537084, | |
| "grad_norm": 0.38572192192077637, | |
| "learning_rate": 1.9785274488395966e-05, | |
| "loss": 0.7409, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 2.7570332480818416, | |
| "grad_norm": 0.4073234498500824, | |
| "learning_rate": 1.9783650601310097e-05, | |
| "loss": 0.7536, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.7672634271099743, | |
| "grad_norm": 0.31672948598861694, | |
| "learning_rate": 1.9782020664061026e-05, | |
| "loss": 0.7461, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 2.7774936061381075, | |
| "grad_norm": 0.3638211786746979, | |
| "learning_rate": 1.978038467765669e-05, | |
| "loss": 0.7545, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 2.78772378516624, | |
| "grad_norm": 0.3304184377193451, | |
| "learning_rate": 1.977874264310877e-05, | |
| "loss": 0.75, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 2.7979539641943734, | |
| "grad_norm": 0.3346056044101715, | |
| "learning_rate": 1.9777094561432707e-05, | |
| "loss": 0.77, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 2.8081841432225065, | |
| "grad_norm": 0.33290547132492065, | |
| "learning_rate": 1.9775440433647662e-05, | |
| "loss": 0.7494, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 2.8184143222506393, | |
| "grad_norm": 0.3400842547416687, | |
| "learning_rate": 1.9773780260776534e-05, | |
| "loss": 0.7658, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 2.8286445012787724, | |
| "grad_norm": 0.36258232593536377, | |
| "learning_rate": 1.9772114043845968e-05, | |
| "loss": 0.7437, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 2.8388746803069056, | |
| "grad_norm": 0.34615638852119446, | |
| "learning_rate": 1.9770441783886348e-05, | |
| "loss": 0.7733, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 2.8491048593350383, | |
| "grad_norm": 0.3608517348766327, | |
| "learning_rate": 1.976876348193179e-05, | |
| "loss": 0.7451, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 2.8593350383631715, | |
| "grad_norm": 0.345670610666275, | |
| "learning_rate": 1.9767079139020148e-05, | |
| "loss": 0.737, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.869565217391304, | |
| "grad_norm": 0.3253295421600342, | |
| "learning_rate": 1.976538875619301e-05, | |
| "loss": 0.7394, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 2.8797953964194374, | |
| "grad_norm": 0.40524566173553467, | |
| "learning_rate": 1.9763692334495706e-05, | |
| "loss": 0.7517, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 2.89002557544757, | |
| "grad_norm": 0.4947255849838257, | |
| "learning_rate": 1.9761989874977287e-05, | |
| "loss": 0.744, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 2.9002557544757033, | |
| "grad_norm": 0.5664758682250977, | |
| "learning_rate": 1.9760281378690554e-05, | |
| "loss": 0.7219, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 2.9104859335038364, | |
| "grad_norm": 0.4397972822189331, | |
| "learning_rate": 1.9758566846692028e-05, | |
| "loss": 0.7301, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 2.920716112531969, | |
| "grad_norm": 0.2917048931121826, | |
| "learning_rate": 1.975684628004197e-05, | |
| "loss": 0.7582, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 2.9309462915601023, | |
| "grad_norm": 0.44785866141319275, | |
| "learning_rate": 1.975511967980437e-05, | |
| "loss": 0.7594, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 2.9411764705882355, | |
| "grad_norm": 0.5528475046157837, | |
| "learning_rate": 1.9753387047046945e-05, | |
| "loss": 0.7289, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 2.9514066496163682, | |
| "grad_norm": 0.5927398800849915, | |
| "learning_rate": 1.9751648382841152e-05, | |
| "loss": 0.7496, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 2.9616368286445014, | |
| "grad_norm": 0.43449971079826355, | |
| "learning_rate": 1.974990368826217e-05, | |
| "loss": 0.7334, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.971867007672634, | |
| "grad_norm": 0.410898357629776, | |
| "learning_rate": 1.9748152964388912e-05, | |
| "loss": 0.7367, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 2.9820971867007673, | |
| "grad_norm": 0.6079134941101074, | |
| "learning_rate": 1.9746396212304018e-05, | |
| "loss": 0.7298, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 2.9923273657289, | |
| "grad_norm": 0.37779679894447327, | |
| "learning_rate": 1.9744633433093852e-05, | |
| "loss": 0.7449, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.38931500911712646, | |
| "learning_rate": 1.974286462784851e-05, | |
| "loss": 0.7486, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 3.010230179028133, | |
| "grad_norm": 0.45001041889190674, | |
| "learning_rate": 1.9741089797661816e-05, | |
| "loss": 0.7467, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 3.020460358056266, | |
| "grad_norm": 0.4439624845981598, | |
| "learning_rate": 1.9739308943631306e-05, | |
| "loss": 0.7217, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 3.030690537084399, | |
| "grad_norm": 0.5038313865661621, | |
| "learning_rate": 1.9737522066858264e-05, | |
| "loss": 0.7262, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 3.040920716112532, | |
| "grad_norm": 0.336954802274704, | |
| "learning_rate": 1.973572916844768e-05, | |
| "loss": 0.7372, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 3.051150895140665, | |
| "grad_norm": 0.5147439241409302, | |
| "learning_rate": 1.9733930249508276e-05, | |
| "loss": 0.7407, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 3.061381074168798, | |
| "grad_norm": 0.6436253190040588, | |
| "learning_rate": 1.973212531115249e-05, | |
| "loss": 0.7124, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.071611253196931, | |
| "grad_norm": 0.322561651468277, | |
| "learning_rate": 1.9730314354496497e-05, | |
| "loss": 0.7462, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 3.081841432225064, | |
| "grad_norm": 1.0073673725128174, | |
| "learning_rate": 1.9728497380660175e-05, | |
| "loss": 0.7351, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 3.0920716112531967, | |
| "grad_norm": 0.8805359601974487, | |
| "learning_rate": 1.9726674390767135e-05, | |
| "loss": 0.7195, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 3.10230179028133, | |
| "grad_norm": 0.7060922980308533, | |
| "learning_rate": 1.9724845385944705e-05, | |
| "loss": 0.7399, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 3.112531969309463, | |
| "grad_norm": 1.5701392889022827, | |
| "learning_rate": 1.9723010367323937e-05, | |
| "loss": 0.7259, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 3.122762148337596, | |
| "grad_norm": 0.5668526291847229, | |
| "learning_rate": 1.972116933603959e-05, | |
| "loss": 0.7188, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 3.132992327365729, | |
| "grad_norm": 0.9209063053131104, | |
| "learning_rate": 1.9719322293230158e-05, | |
| "loss": 0.7248, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 3.1432225063938617, | |
| "grad_norm": 0.6814517378807068, | |
| "learning_rate": 1.9717469240037835e-05, | |
| "loss": 0.7404, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 3.153452685421995, | |
| "grad_norm": 1.6327886581420898, | |
| "learning_rate": 1.9715610177608547e-05, | |
| "loss": 0.7392, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 3.163682864450128, | |
| "grad_norm": 0.8322291970252991, | |
| "learning_rate": 1.9713745107091924e-05, | |
| "loss": 0.7244, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 3.1739130434782608, | |
| "grad_norm": 0.9853781461715698, | |
| "learning_rate": 1.971187402964132e-05, | |
| "loss": 0.7342, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 3.184143222506394, | |
| "grad_norm": 0.869482159614563, | |
| "learning_rate": 1.97099969464138e-05, | |
| "loss": 0.7376, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 3.1943734015345266, | |
| "grad_norm": 0.5311108827590942, | |
| "learning_rate": 1.9708113858570143e-05, | |
| "loss": 0.7339, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 3.20460358056266, | |
| "grad_norm": 1.897441029548645, | |
| "learning_rate": 1.9706224767274844e-05, | |
| "loss": 0.7537, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 3.214833759590793, | |
| "grad_norm": 1.1312215328216553, | |
| "learning_rate": 1.9704329673696104e-05, | |
| "loss": 0.7368, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 3.2250639386189257, | |
| "grad_norm": 0.859919548034668, | |
| "learning_rate": 1.9702428579005844e-05, | |
| "loss": 0.7492, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 3.235294117647059, | |
| "grad_norm": 0.8550412654876709, | |
| "learning_rate": 1.9700521484379687e-05, | |
| "loss": 0.7204, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 3.2455242966751916, | |
| "grad_norm": 0.6723067164421082, | |
| "learning_rate": 1.9698608390996975e-05, | |
| "loss": 0.7349, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 3.2557544757033248, | |
| "grad_norm": 0.7956928610801697, | |
| "learning_rate": 1.9696689300040758e-05, | |
| "loss": 0.738, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 3.265984654731458, | |
| "grad_norm": 1.1205618381500244, | |
| "learning_rate": 1.9694764212697784e-05, | |
| "loss": 0.7219, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 3.2762148337595907, | |
| "grad_norm": 0.4344213008880615, | |
| "learning_rate": 1.9692833130158528e-05, | |
| "loss": 0.7473, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 3.286445012787724, | |
| "grad_norm": 0.8046640157699585, | |
| "learning_rate": 1.9690896053617156e-05, | |
| "loss": 0.736, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 3.296675191815857, | |
| "grad_norm": 0.5893542170524597, | |
| "learning_rate": 1.968895298427155e-05, | |
| "loss": 0.7178, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 3.3069053708439897, | |
| "grad_norm": 0.543119490146637, | |
| "learning_rate": 1.9687003923323292e-05, | |
| "loss": 0.7386, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 3.317135549872123, | |
| "grad_norm": 0.9876613616943359, | |
| "learning_rate": 1.9685048871977678e-05, | |
| "loss": 0.732, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 3.3273657289002556, | |
| "grad_norm": 0.42082035541534424, | |
| "learning_rate": 1.968308783144369e-05, | |
| "loss": 0.7272, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 3.337595907928389, | |
| "grad_norm": 0.7916600108146667, | |
| "learning_rate": 1.9681120802934042e-05, | |
| "loss": 0.7303, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 3.3478260869565215, | |
| "grad_norm": 0.6041877865791321, | |
| "learning_rate": 1.9679147787665128e-05, | |
| "loss": 0.7395, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 3.3580562659846547, | |
| "grad_norm": 0.8722060918807983, | |
| "learning_rate": 1.9677168786857044e-05, | |
| "loss": 0.7226, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 3.368286445012788, | |
| "grad_norm": 0.577777624130249, | |
| "learning_rate": 1.967518380173361e-05, | |
| "loss": 0.7301, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 3.3785166240409206, | |
| "grad_norm": 0.5443961024284363, | |
| "learning_rate": 1.967319283352232e-05, | |
| "loss": 0.7355, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 3.3887468030690537, | |
| "grad_norm": 0.695266842842102, | |
| "learning_rate": 1.967119588345438e-05, | |
| "loss": 0.7361, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 3.398976982097187, | |
| "grad_norm": 0.41574743390083313, | |
| "learning_rate": 1.9669192952764698e-05, | |
| "loss": 0.7307, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 3.4092071611253196, | |
| "grad_norm": 0.9063800573348999, | |
| "learning_rate": 1.9667184042691877e-05, | |
| "loss": 0.7374, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 3.419437340153453, | |
| "grad_norm": 0.45360273122787476, | |
| "learning_rate": 1.9665169154478214e-05, | |
| "loss": 0.7449, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 3.4296675191815855, | |
| "grad_norm": 0.6068630218505859, | |
| "learning_rate": 1.966314828936971e-05, | |
| "loss": 0.7381, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 3.4398976982097187, | |
| "grad_norm": 0.5979428291320801, | |
| "learning_rate": 1.9661121448616057e-05, | |
| "loss": 0.736, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 3.4501278772378514, | |
| "grad_norm": 0.5259372591972351, | |
| "learning_rate": 1.9659088633470646e-05, | |
| "loss": 0.7411, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 3.4603580562659846, | |
| "grad_norm": 0.7314724326133728, | |
| "learning_rate": 1.965704984519055e-05, | |
| "loss": 0.7396, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 3.4705882352941178, | |
| "grad_norm": 0.40047791600227356, | |
| "learning_rate": 1.9655005085036563e-05, | |
| "loss": 0.696, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 3.4808184143222505, | |
| "grad_norm": 0.6751558780670166, | |
| "learning_rate": 1.965295435427314e-05, | |
| "loss": 0.7283, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 3.4910485933503836, | |
| "grad_norm": 0.4402068853378296, | |
| "learning_rate": 1.965089765416845e-05, | |
| "loss": 0.7171, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 3.501278772378517, | |
| "grad_norm": 0.8496968746185303, | |
| "learning_rate": 1.964883498599435e-05, | |
| "loss": 0.7121, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 3.5115089514066495, | |
| "grad_norm": 0.42892828583717346, | |
| "learning_rate": 1.9646766351026378e-05, | |
| "loss": 0.7461, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 3.5217391304347827, | |
| "grad_norm": 0.6416417956352234, | |
| "learning_rate": 1.964469175054377e-05, | |
| "loss": 0.7429, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 3.531969309462916, | |
| "grad_norm": 0.361579030752182, | |
| "learning_rate": 1.9642611185829444e-05, | |
| "loss": 0.7302, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 3.5421994884910486, | |
| "grad_norm": 0.5479419231414795, | |
| "learning_rate": 1.9640524658170023e-05, | |
| "loss": 0.7304, | |
| "step": 347 | |
| }, | |
| { | |
| "epoch": 3.5524296675191813, | |
| "grad_norm": 0.4338844418525696, | |
| "learning_rate": 1.9638432168855797e-05, | |
| "loss": 0.6999, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 3.5626598465473145, | |
| "grad_norm": 0.5022692680358887, | |
| "learning_rate": 1.9636333719180755e-05, | |
| "loss": 0.7068, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 3.5728900255754477, | |
| "grad_norm": 0.4946191608905792, | |
| "learning_rate": 1.9634229310442564e-05, | |
| "loss": 0.7336, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 3.5831202046035804, | |
| "grad_norm": 0.5408332943916321, | |
| "learning_rate": 1.9632118943942587e-05, | |
| "loss": 0.741, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 3.5933503836317136, | |
| "grad_norm": 0.7036914825439453, | |
| "learning_rate": 1.9630002620985856e-05, | |
| "loss": 0.7257, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 3.6035805626598467, | |
| "grad_norm": 0.5046015977859497, | |
| "learning_rate": 1.9627880342881106e-05, | |
| "loss": 0.729, | |
| "step": 353 | |
| }, | |
| { | |
| "epoch": 3.6138107416879794, | |
| "grad_norm": 0.632416307926178, | |
| "learning_rate": 1.9625752110940736e-05, | |
| "loss": 0.7089, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 3.6240409207161126, | |
| "grad_norm": 0.3495820164680481, | |
| "learning_rate": 1.962361792648084e-05, | |
| "loss": 0.7391, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 3.634271099744246, | |
| "grad_norm": 0.9268649816513062, | |
| "learning_rate": 1.962147779082118e-05, | |
| "loss": 0.7361, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 3.6445012787723785, | |
| "grad_norm": 0.5460264086723328, | |
| "learning_rate": 1.961933170528521e-05, | |
| "loss": 0.7213, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 3.6547314578005117, | |
| "grad_norm": 0.6042870283126831, | |
| "learning_rate": 1.961717967120006e-05, | |
| "loss": 0.7295, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 3.6649616368286444, | |
| "grad_norm": 0.4831192195415497, | |
| "learning_rate": 1.9615021689896533e-05, | |
| "loss": 0.7404, | |
| "step": 359 | |
| }, | |
| { | |
| "epoch": 3.6751918158567776, | |
| "grad_norm": 0.8810766935348511, | |
| "learning_rate": 1.9612857762709122e-05, | |
| "loss": 0.7192, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 3.6854219948849103, | |
| "grad_norm": 0.4142047166824341, | |
| "learning_rate": 1.961068789097599e-05, | |
| "loss": 0.7352, | |
| "step": 361 | |
| }, | |
| { | |
| "epoch": 3.6956521739130435, | |
| "grad_norm": 0.6235917806625366, | |
| "learning_rate": 1.9608512076038964e-05, | |
| "loss": 0.7345, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 3.7058823529411766, | |
| "grad_norm": 0.4514963626861572, | |
| "learning_rate": 1.9606330319243568e-05, | |
| "loss": 0.721, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 3.7161125319693094, | |
| "grad_norm": 0.7020410299301147, | |
| "learning_rate": 1.9604142621938986e-05, | |
| "loss": 0.7126, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 3.7263427109974425, | |
| "grad_norm": 0.3949349820613861, | |
| "learning_rate": 1.9601948985478078e-05, | |
| "loss": 0.7412, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 3.7365728900255757, | |
| "grad_norm": 0.6317225098609924, | |
| "learning_rate": 1.9599749411217385e-05, | |
| "loss": 0.7418, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 3.7468030690537084, | |
| "grad_norm": 0.41394850611686707, | |
| "learning_rate": 1.9597543900517106e-05, | |
| "loss": 0.7051, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 3.7570332480818416, | |
| "grad_norm": 0.6289117336273193, | |
| "learning_rate": 1.959533245474112e-05, | |
| "loss": 0.7397, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 3.7672634271099743, | |
| "grad_norm": 0.5273838639259338, | |
| "learning_rate": 1.9593115075256978e-05, | |
| "loss": 0.7129, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 3.7774936061381075, | |
| "grad_norm": 0.4530670940876007, | |
| "learning_rate": 1.9590891763435892e-05, | |
| "loss": 0.7211, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 3.78772378516624, | |
| "grad_norm": 0.5219662189483643, | |
| "learning_rate": 1.9588662520652756e-05, | |
| "loss": 0.732, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 3.7979539641943734, | |
| "grad_norm": 0.4979133605957031, | |
| "learning_rate": 1.958642734828611e-05, | |
| "loss": 0.7375, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 3.8081841432225065, | |
| "grad_norm": 0.5304292440414429, | |
| "learning_rate": 1.958418624771819e-05, | |
| "loss": 0.7349, | |
| "step": 373 | |
| }, | |
| { | |
| "epoch": 3.8184143222506393, | |
| "grad_norm": 0.4747787117958069, | |
| "learning_rate": 1.958193922033487e-05, | |
| "loss": 0.7338, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 3.8286445012787724, | |
| "grad_norm": 0.451325923204422, | |
| "learning_rate": 1.9579686267525704e-05, | |
| "loss": 0.7084, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 3.8388746803069056, | |
| "grad_norm": 0.43068253993988037, | |
| "learning_rate": 1.957742739068391e-05, | |
| "loss": 0.7348, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 3.8491048593350383, | |
| "grad_norm": 0.4494073987007141, | |
| "learning_rate": 1.9575162591206362e-05, | |
| "loss": 0.7466, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 3.8593350383631715, | |
| "grad_norm": 0.46458712220191956, | |
| "learning_rate": 1.9572891870493604e-05, | |
| "loss": 0.7257, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 3.869565217391304, | |
| "grad_norm": 0.4800684452056885, | |
| "learning_rate": 1.9570615229949844e-05, | |
| "loss": 0.7171, | |
| "step": 379 | |
| }, | |
| { | |
| "epoch": 3.8797953964194374, | |
| "grad_norm": 0.4564310312271118, | |
| "learning_rate": 1.9568332670982934e-05, | |
| "loss": 0.7225, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 3.89002557544757, | |
| "grad_norm": 0.39550548791885376, | |
| "learning_rate": 1.956604419500441e-05, | |
| "loss": 0.7119, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 3.9002557544757033, | |
| "grad_norm": 0.4126419425010681, | |
| "learning_rate": 1.9563749803429447e-05, | |
| "loss": 0.7359, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 3.9104859335038364, | |
| "grad_norm": 0.4096467196941376, | |
| "learning_rate": 1.9561449497676888e-05, | |
| "loss": 0.7322, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 3.920716112531969, | |
| "grad_norm": 0.407622754573822, | |
| "learning_rate": 1.955914327916923e-05, | |
| "loss": 0.7202, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 3.9309462915601023, | |
| "grad_norm": 0.363885760307312, | |
| "learning_rate": 1.955683114933263e-05, | |
| "loss": 0.7171, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 3.9411764705882355, | |
| "grad_norm": 0.3362027704715729, | |
| "learning_rate": 1.9554513109596898e-05, | |
| "loss": 0.717, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 3.9514066496163682, | |
| "grad_norm": 0.3913104832172394, | |
| "learning_rate": 1.9552189161395496e-05, | |
| "loss": 0.7141, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 3.9616368286445014, | |
| "grad_norm": 0.3984425961971283, | |
| "learning_rate": 1.9549859306165543e-05, | |
| "loss": 0.7404, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 3.971867007672634, | |
| "grad_norm": 0.4172505736351013, | |
| "learning_rate": 1.9547523545347816e-05, | |
| "loss": 0.7402, | |
| "step": 389 | |
| }, | |
| { | |
| "epoch": 3.9820971867007673, | |
| "grad_norm": 0.3991503119468689, | |
| "learning_rate": 1.954518188038673e-05, | |
| "loss": 0.7306, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 3.9923273657289, | |
| "grad_norm": 0.5286377668380737, | |
| "learning_rate": 1.9542834312730366e-05, | |
| "loss": 0.728, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.49067217111587524, | |
| "learning_rate": 1.9540480843830443e-05, | |
| "loss": 0.7302, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 4.010230179028133, | |
| "grad_norm": 0.7454357147216797, | |
| "learning_rate": 1.9538121475142345e-05, | |
| "loss": 0.7218, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 4.020460358056266, | |
| "grad_norm": 0.44008755683898926, | |
| "learning_rate": 1.9535756208125082e-05, | |
| "loss": 0.716, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 4.030690537084399, | |
| "grad_norm": 0.6294509172439575, | |
| "learning_rate": 1.9533385044241335e-05, | |
| "loss": 0.7321, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 4.040920716112532, | |
| "grad_norm": 0.46539950370788574, | |
| "learning_rate": 1.9531007984957408e-05, | |
| "loss": 0.742, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 4.051150895140665, | |
| "grad_norm": 0.6322250366210938, | |
| "learning_rate": 1.9528625031743278e-05, | |
| "loss": 0.7217, | |
| "step": 397 | |
| }, | |
| { | |
| "epoch": 4.061381074168798, | |
| "grad_norm": 0.5787230134010315, | |
| "learning_rate": 1.952623618607254e-05, | |
| "loss": 0.7298, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 4.071611253196931, | |
| "grad_norm": 0.5471862554550171, | |
| "learning_rate": 1.952384144942245e-05, | |
| "loss": 0.7135, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 4.081841432225064, | |
| "grad_norm": 0.543489396572113, | |
| "learning_rate": 1.9521440823273902e-05, | |
| "loss": 0.7164, | |
| "step": 400 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 4000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 42, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.570007282502746e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |