| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.995749704840614, | |
| "eval_steps": 500, | |
| "global_step": 6348, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 1.1830811500549316, | |
| "learning_rate": 1.1811023622047244e-06, | |
| "loss": 2.1629, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 1.7049249410629272, | |
| "learning_rate": 2.3622047244094487e-06, | |
| "loss": 2.1307, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 1.4969309568405151, | |
| "learning_rate": 3.543307086614173e-06, | |
| "loss": 2.112, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.9817995429039001, | |
| "learning_rate": 4.7244094488188975e-06, | |
| "loss": 1.9605, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.7148410677909851, | |
| "learning_rate": 5.905511811023622e-06, | |
| "loss": 1.8467, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.4169553518295288, | |
| "learning_rate": 7.086614173228346e-06, | |
| "loss": 1.6873, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.40290525555610657, | |
| "learning_rate": 8.267716535433071e-06, | |
| "loss": 1.5778, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.2909008860588074, | |
| "learning_rate": 9.448818897637795e-06, | |
| "loss": 1.528, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.2634272873401642, | |
| "learning_rate": 1.0629921259842519e-05, | |
| "loss": 1.432, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.2529142200946808, | |
| "learning_rate": 1.1811023622047245e-05, | |
| "loss": 1.392, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.2729162573814392, | |
| "learning_rate": 1.2992125984251968e-05, | |
| "loss": 1.3803, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.29093897342681885, | |
| "learning_rate": 1.4173228346456692e-05, | |
| "loss": 1.2938, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 0.3456454873085022, | |
| "learning_rate": 1.5354330708661416e-05, | |
| "loss": 1.2638, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 0.2981075346469879, | |
| "learning_rate": 1.6535433070866142e-05, | |
| "loss": 1.2191, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 0.26900631189346313, | |
| "learning_rate": 1.7716535433070864e-05, | |
| "loss": 1.1489, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 0.31342336535453796, | |
| "learning_rate": 1.889763779527559e-05, | |
| "loss": 1.1289, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.3491218388080597, | |
| "learning_rate": 2.0078740157480316e-05, | |
| "loss": 1.0612, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 0.36805489659309387, | |
| "learning_rate": 2.1259842519685038e-05, | |
| "loss": 1.1026, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 0.36568203568458557, | |
| "learning_rate": 2.2440944881889763e-05, | |
| "loss": 1.0621, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 0.41116490960121155, | |
| "learning_rate": 2.362204724409449e-05, | |
| "loss": 1.0184, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.4134870171546936, | |
| "learning_rate": 2.480314960629921e-05, | |
| "loss": 1.0015, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.4291512966156006, | |
| "learning_rate": 2.5984251968503937e-05, | |
| "loss": 0.9931, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 0.5563335418701172, | |
| "learning_rate": 2.716535433070866e-05, | |
| "loss": 0.9914, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 0.41773471236228943, | |
| "learning_rate": 2.8346456692913385e-05, | |
| "loss": 0.9395, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 0.4548351466655731, | |
| "learning_rate": 2.952755905511811e-05, | |
| "loss": 0.958, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 0.515271782875061, | |
| "learning_rate": 2.9921232277262383e-05, | |
| "loss": 0.9497, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.4861299693584442, | |
| "learning_rate": 2.978995273936636e-05, | |
| "loss": 0.915, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 0.5384882688522339, | |
| "learning_rate": 2.965867320147033e-05, | |
| "loss": 0.9498, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.5463869571685791, | |
| "learning_rate": 2.9527393663574304e-05, | |
| "loss": 0.934, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 0.5710709691047668, | |
| "learning_rate": 2.939611412567828e-05, | |
| "loss": 0.9273, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 0.6447290778160095, | |
| "learning_rate": 2.9264834587782252e-05, | |
| "loss": 0.895, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.5392516851425171, | |
| "learning_rate": 2.9133555049886224e-05, | |
| "loss": 0.8863, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 0.5963829159736633, | |
| "learning_rate": 2.90022755119902e-05, | |
| "loss": 0.8505, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.6194504499435425, | |
| "learning_rate": 2.8870995974094173e-05, | |
| "loss": 0.9034, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": 0.5820630192756653, | |
| "learning_rate": 2.873971643619815e-05, | |
| "loss": 0.9087, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 0.5965354442596436, | |
| "learning_rate": 2.8608436898302117e-05, | |
| "loss": 0.8652, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 0.5949137210845947, | |
| "learning_rate": 2.847715736040609e-05, | |
| "loss": 0.8323, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 0.5632292032241821, | |
| "learning_rate": 2.8345877822510066e-05, | |
| "loss": 0.8636, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 0.600488543510437, | |
| "learning_rate": 2.8214598284614038e-05, | |
| "loss": 0.8467, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 0.6131569743156433, | |
| "learning_rate": 2.808331874671801e-05, | |
| "loss": 0.8394, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": 0.6562418937683105, | |
| "learning_rate": 2.7952039208821986e-05, | |
| "loss": 0.8393, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": 0.6331117153167725, | |
| "learning_rate": 2.782075967092596e-05, | |
| "loss": 0.8631, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 0.667453944683075, | |
| "learning_rate": 2.7689480133029935e-05, | |
| "loss": 0.8447, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 0.6880422830581665, | |
| "learning_rate": 2.7558200595133907e-05, | |
| "loss": 0.807, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "grad_norm": 0.7089916467666626, | |
| "learning_rate": 2.742692105723788e-05, | |
| "loss": 0.8229, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "grad_norm": 0.6905713081359863, | |
| "learning_rate": 2.7295641519341855e-05, | |
| "loss": 0.8455, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "grad_norm": 0.6697952151298523, | |
| "learning_rate": 2.7164361981445824e-05, | |
| "loss": 0.8241, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "grad_norm": 0.6053146123886108, | |
| "learning_rate": 2.7033082443549797e-05, | |
| "loss": 0.85, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 0.62926185131073, | |
| "learning_rate": 2.6901802905653773e-05, | |
| "loss": 0.8541, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "grad_norm": 0.7045501470565796, | |
| "learning_rate": 2.6770523367757745e-05, | |
| "loss": 0.8678, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 0.7079373598098755, | |
| "learning_rate": 2.663924382986172e-05, | |
| "loss": 0.8119, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "grad_norm": 0.6754956841468811, | |
| "learning_rate": 2.6507964291965693e-05, | |
| "loss": 0.8201, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 0.7645794749259949, | |
| "learning_rate": 2.6376684754069666e-05, | |
| "loss": 0.8103, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 0.7001616358757019, | |
| "learning_rate": 2.624540521617364e-05, | |
| "loss": 0.8116, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 0.7295788526535034, | |
| "learning_rate": 2.6114125678277614e-05, | |
| "loss": 0.8106, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 0.7286357879638672, | |
| "learning_rate": 2.5982846140381586e-05, | |
| "loss": 0.8154, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "grad_norm": 0.6777210235595703, | |
| "learning_rate": 2.5851566602485562e-05, | |
| "loss": 0.8193, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "grad_norm": 0.7970985174179077, | |
| "learning_rate": 2.5720287064589535e-05, | |
| "loss": 0.8118, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "grad_norm": 0.7872875928878784, | |
| "learning_rate": 2.5589007526693504e-05, | |
| "loss": 0.829, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "grad_norm": 0.6874305009841919, | |
| "learning_rate": 2.545772798879748e-05, | |
| "loss": 0.7935, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 0.8056828379631042, | |
| "learning_rate": 2.5326448450901452e-05, | |
| "loss": 0.8077, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "grad_norm": 0.7361560463905334, | |
| "learning_rate": 2.5195168913005428e-05, | |
| "loss": 0.8179, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "grad_norm": 0.7530879378318787, | |
| "learning_rate": 2.50638893751094e-05, | |
| "loss": 0.7939, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "grad_norm": 0.7077944874763489, | |
| "learning_rate": 2.4932609837213373e-05, | |
| "loss": 0.8158, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "grad_norm": 0.7000440955162048, | |
| "learning_rate": 2.480133029931735e-05, | |
| "loss": 0.8224, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 0.6929032206535339, | |
| "learning_rate": 2.467005076142132e-05, | |
| "loss": 0.8073, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "grad_norm": 0.6915440559387207, | |
| "learning_rate": 2.4538771223525293e-05, | |
| "loss": 0.8055, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "grad_norm": 0.79297935962677, | |
| "learning_rate": 2.440749168562927e-05, | |
| "loss": 0.7866, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "grad_norm": 0.7547681927680969, | |
| "learning_rate": 2.427621214773324e-05, | |
| "loss": 0.8039, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "grad_norm": 0.7506528496742249, | |
| "learning_rate": 2.4144932609837214e-05, | |
| "loss": 0.7823, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "grad_norm": 0.7495055198669434, | |
| "learning_rate": 2.4013653071941186e-05, | |
| "loss": 0.7917, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "grad_norm": 0.725407600402832, | |
| "learning_rate": 2.388237353404516e-05, | |
| "loss": 0.8195, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "grad_norm": 0.7200865745544434, | |
| "learning_rate": 2.3751093996149135e-05, | |
| "loss": 0.7682, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 0.8560680747032166, | |
| "learning_rate": 2.3619814458253107e-05, | |
| "loss": 0.7862, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "grad_norm": 0.7104244828224182, | |
| "learning_rate": 2.348853492035708e-05, | |
| "loss": 0.8058, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "grad_norm": 0.7858747839927673, | |
| "learning_rate": 2.3357255382461055e-05, | |
| "loss": 0.7787, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "grad_norm": 0.8110267519950867, | |
| "learning_rate": 2.3225975844565028e-05, | |
| "loss": 0.7896, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "grad_norm": 0.7881801128387451, | |
| "learning_rate": 2.3094696306669004e-05, | |
| "loss": 0.7637, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "grad_norm": 0.7833150625228882, | |
| "learning_rate": 2.2963416768772976e-05, | |
| "loss": 0.7755, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "grad_norm": 0.747809886932373, | |
| "learning_rate": 2.283213723087695e-05, | |
| "loss": 0.7449, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "grad_norm": 0.8134004473686218, | |
| "learning_rate": 2.270085769298092e-05, | |
| "loss": 0.7972, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "grad_norm": 0.801780641078949, | |
| "learning_rate": 2.2569578155084893e-05, | |
| "loss": 0.7584, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 0.7908413410186768, | |
| "learning_rate": 2.2438298617188866e-05, | |
| "loss": 0.7783, | |
| "step": 2075 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "grad_norm": 0.7693101167678833, | |
| "learning_rate": 2.230701907929284e-05, | |
| "loss": 0.785, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "grad_norm": 0.7623382210731506, | |
| "learning_rate": 2.2175739541396814e-05, | |
| "loss": 0.8268, | |
| "step": 2125 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "grad_norm": 0.744848906993866, | |
| "learning_rate": 2.2044460003500787e-05, | |
| "loss": 0.8011, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "grad_norm": 0.8488389849662781, | |
| "learning_rate": 2.1913180465604762e-05, | |
| "loss": 0.7635, | |
| "step": 2175 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "grad_norm": 0.6634330153465271, | |
| "learning_rate": 2.1781900927708735e-05, | |
| "loss": 0.7519, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "grad_norm": 0.837360680103302, | |
| "learning_rate": 2.165062138981271e-05, | |
| "loss": 0.7826, | |
| "step": 2225 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "grad_norm": 1.0188002586364746, | |
| "learning_rate": 2.1519341851916683e-05, | |
| "loss": 0.7705, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "grad_norm": 0.7619863152503967, | |
| "learning_rate": 2.1388062314020655e-05, | |
| "loss": 0.7823, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "grad_norm": 0.781378448009491, | |
| "learning_rate": 2.1256782776124628e-05, | |
| "loss": 0.769, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "grad_norm": 0.7792461514472961, | |
| "learning_rate": 2.11255032382286e-05, | |
| "loss": 0.7791, | |
| "step": 2325 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "grad_norm": 0.8438695669174194, | |
| "learning_rate": 2.0994223700332573e-05, | |
| "loss": 0.7616, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "grad_norm": 0.7547187805175781, | |
| "learning_rate": 2.086294416243655e-05, | |
| "loss": 0.766, | |
| "step": 2375 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "grad_norm": 0.7716125249862671, | |
| "learning_rate": 2.073166462454052e-05, | |
| "loss": 0.7596, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "grad_norm": 0.8215446472167969, | |
| "learning_rate": 2.0600385086644497e-05, | |
| "loss": 0.7801, | |
| "step": 2425 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "grad_norm": 0.8171260952949524, | |
| "learning_rate": 2.046910554874847e-05, | |
| "loss": 0.757, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "grad_norm": 0.7741256952285767, | |
| "learning_rate": 2.0337826010852442e-05, | |
| "loss": 0.773, | |
| "step": 2475 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "grad_norm": 0.9329236149787903, | |
| "learning_rate": 2.0206546472956418e-05, | |
| "loss": 0.7859, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "grad_norm": 0.8117268681526184, | |
| "learning_rate": 2.007526693506039e-05, | |
| "loss": 0.7277, | |
| "step": 2525 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "grad_norm": 0.793161928653717, | |
| "learning_rate": 1.9943987397164362e-05, | |
| "loss": 0.7643, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "grad_norm": 0.766437828540802, | |
| "learning_rate": 1.9812707859268338e-05, | |
| "loss": 0.79, | |
| "step": 2575 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "grad_norm": 0.8206325173377991, | |
| "learning_rate": 1.9681428321372307e-05, | |
| "loss": 0.7662, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "grad_norm": 0.7363426685333252, | |
| "learning_rate": 1.9550148783476283e-05, | |
| "loss": 0.7887, | |
| "step": 2625 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 0.7617402672767639, | |
| "learning_rate": 1.9418869245580256e-05, | |
| "loss": 0.771, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "grad_norm": 0.7949870824813843, | |
| "learning_rate": 1.9287589707684228e-05, | |
| "loss": 0.7358, | |
| "step": 2675 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "grad_norm": 0.8213860392570496, | |
| "learning_rate": 1.9156310169788204e-05, | |
| "loss": 0.7434, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "grad_norm": 0.8030453324317932, | |
| "learning_rate": 1.9025030631892176e-05, | |
| "loss": 0.7535, | |
| "step": 2725 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "grad_norm": 0.7638863921165466, | |
| "learning_rate": 1.889375109399615e-05, | |
| "loss": 0.7735, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "grad_norm": 0.7628746628761292, | |
| "learning_rate": 1.8762471556100124e-05, | |
| "loss": 0.7749, | |
| "step": 2775 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "grad_norm": 0.7935550808906555, | |
| "learning_rate": 1.8631192018204097e-05, | |
| "loss": 0.7527, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "grad_norm": 0.7617929577827454, | |
| "learning_rate": 1.8499912480308073e-05, | |
| "loss": 0.7672, | |
| "step": 2825 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "grad_norm": 0.7850877642631531, | |
| "learning_rate": 1.8368632942412045e-05, | |
| "loss": 0.7802, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "grad_norm": 0.8149070739746094, | |
| "learning_rate": 1.8237353404516014e-05, | |
| "loss": 0.785, | |
| "step": 2875 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "grad_norm": 0.8640419840812683, | |
| "learning_rate": 1.810607386661999e-05, | |
| "loss": 0.796, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "grad_norm": 0.8122150897979736, | |
| "learning_rate": 1.7974794328723962e-05, | |
| "loss": 0.764, | |
| "step": 2925 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "grad_norm": 0.7679978013038635, | |
| "learning_rate": 1.7843514790827935e-05, | |
| "loss": 0.7656, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "grad_norm": 0.8210141658782959, | |
| "learning_rate": 1.771223525293191e-05, | |
| "loss": 0.7408, | |
| "step": 2975 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "grad_norm": 0.8836562633514404, | |
| "learning_rate": 1.7580955715035883e-05, | |
| "loss": 0.7599, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "grad_norm": 0.8436664342880249, | |
| "learning_rate": 1.7449676177139856e-05, | |
| "loss": 0.7245, | |
| "step": 3025 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "grad_norm": 0.7050043940544128, | |
| "learning_rate": 1.731839663924383e-05, | |
| "loss": 0.7428, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "grad_norm": 0.8637681603431702, | |
| "learning_rate": 1.7187117101347804e-05, | |
| "loss": 0.7336, | |
| "step": 3075 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "grad_norm": 0.8028432726860046, | |
| "learning_rate": 1.705583756345178e-05, | |
| "loss": 0.7803, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "grad_norm": 0.8453486561775208, | |
| "learning_rate": 1.6924558025555752e-05, | |
| "loss": 0.8016, | |
| "step": 3125 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "grad_norm": 0.8883052468299866, | |
| "learning_rate": 1.679327848765972e-05, | |
| "loss": 0.7431, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.8956327438354492, | |
| "learning_rate": 1.6661998949763697e-05, | |
| "loss": 0.7743, | |
| "step": 3175 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "grad_norm": 0.7592474222183228, | |
| "learning_rate": 1.653071941186767e-05, | |
| "loss": 0.7287, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "grad_norm": 0.9048654437065125, | |
| "learning_rate": 1.6399439873971642e-05, | |
| "loss": 0.7576, | |
| "step": 3225 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "grad_norm": 0.7991531491279602, | |
| "learning_rate": 1.6268160336075618e-05, | |
| "loss": 0.7564, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "grad_norm": 0.814805269241333, | |
| "learning_rate": 1.613688079817959e-05, | |
| "loss": 0.7562, | |
| "step": 3275 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "grad_norm": 0.8084884285926819, | |
| "learning_rate": 1.6005601260283566e-05, | |
| "loss": 0.7654, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "grad_norm": 0.8876549601554871, | |
| "learning_rate": 1.587432172238754e-05, | |
| "loss": 0.7366, | |
| "step": 3325 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "grad_norm": 0.8986101150512695, | |
| "learning_rate": 1.574304218449151e-05, | |
| "loss": 0.7451, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "grad_norm": 0.826542854309082, | |
| "learning_rate": 1.5611762646595487e-05, | |
| "loss": 0.7708, | |
| "step": 3375 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "grad_norm": 0.8317553997039795, | |
| "learning_rate": 1.548048310869946e-05, | |
| "loss": 0.7273, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "grad_norm": 0.820817232131958, | |
| "learning_rate": 1.5349203570803428e-05, | |
| "loss": 0.7797, | |
| "step": 3425 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "grad_norm": 0.8864796757698059, | |
| "learning_rate": 1.5217924032907404e-05, | |
| "loss": 0.7653, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "grad_norm": 0.8678339123725891, | |
| "learning_rate": 1.5086644495011376e-05, | |
| "loss": 0.7488, | |
| "step": 3475 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "grad_norm": 0.8052393198013306, | |
| "learning_rate": 1.495536495711535e-05, | |
| "loss": 0.6971, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "grad_norm": 0.8921340703964233, | |
| "learning_rate": 1.4824085419219325e-05, | |
| "loss": 0.7846, | |
| "step": 3525 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "grad_norm": 0.823711097240448, | |
| "learning_rate": 1.4692805881323299e-05, | |
| "loss": 0.765, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "grad_norm": 0.8947944641113281, | |
| "learning_rate": 1.4561526343427271e-05, | |
| "loss": 0.7597, | |
| "step": 3575 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "grad_norm": 0.9127305746078491, | |
| "learning_rate": 1.4430246805531245e-05, | |
| "loss": 0.7359, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "grad_norm": 0.8424604535102844, | |
| "learning_rate": 1.429896726763522e-05, | |
| "loss": 0.7678, | |
| "step": 3625 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "grad_norm": 0.7486136555671692, | |
| "learning_rate": 1.4167687729739192e-05, | |
| "loss": 0.7801, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "grad_norm": 0.9274526834487915, | |
| "learning_rate": 1.4036408191843164e-05, | |
| "loss": 0.7456, | |
| "step": 3675 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "grad_norm": 0.8695843815803528, | |
| "learning_rate": 1.3905128653947138e-05, | |
| "loss": 0.7412, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "grad_norm": 0.881801426410675, | |
| "learning_rate": 1.3773849116051113e-05, | |
| "loss": 0.7626, | |
| "step": 3725 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "grad_norm": 0.9325851798057556, | |
| "learning_rate": 1.3642569578155085e-05, | |
| "loss": 0.7803, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "grad_norm": 0.8312095403671265, | |
| "learning_rate": 1.3511290040259059e-05, | |
| "loss": 0.7396, | |
| "step": 3775 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "grad_norm": 0.8334879279136658, | |
| "learning_rate": 1.3380010502363032e-05, | |
| "loss": 0.7402, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "grad_norm": 0.8369125723838806, | |
| "learning_rate": 1.3248730964467006e-05, | |
| "loss": 0.7308, | |
| "step": 3825 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "grad_norm": 0.7799876928329468, | |
| "learning_rate": 1.3117451426570978e-05, | |
| "loss": 0.7249, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "grad_norm": 0.841027021408081, | |
| "learning_rate": 1.2986171888674952e-05, | |
| "loss": 0.7235, | |
| "step": 3875 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "grad_norm": 0.8014695644378662, | |
| "learning_rate": 1.2854892350778926e-05, | |
| "loss": 0.7234, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "grad_norm": 0.7508646249771118, | |
| "learning_rate": 1.2723612812882899e-05, | |
| "loss": 0.7556, | |
| "step": 3925 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "grad_norm": 0.7451643943786621, | |
| "learning_rate": 1.2592333274986871e-05, | |
| "loss": 0.7268, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "grad_norm": 0.8782030940055847, | |
| "learning_rate": 1.2461053737090845e-05, | |
| "loss": 0.7357, | |
| "step": 3975 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "grad_norm": 0.8773329257965088, | |
| "learning_rate": 1.232977419919482e-05, | |
| "loss": 0.7559, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "grad_norm": 0.866611123085022, | |
| "learning_rate": 1.2198494661298794e-05, | |
| "loss": 0.7314, | |
| "step": 4025 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "grad_norm": 0.9285776615142822, | |
| "learning_rate": 1.2067215123402766e-05, | |
| "loss": 0.7459, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "grad_norm": 0.8246288299560547, | |
| "learning_rate": 1.1935935585506738e-05, | |
| "loss": 0.7536, | |
| "step": 4075 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "grad_norm": 0.9669488668441772, | |
| "learning_rate": 1.1804656047610713e-05, | |
| "loss": 0.758, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "grad_norm": 0.8978260159492493, | |
| "learning_rate": 1.1673376509714687e-05, | |
| "loss": 0.7262, | |
| "step": 4125 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "grad_norm": 0.8229988217353821, | |
| "learning_rate": 1.154209697181866e-05, | |
| "loss": 0.7331, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "grad_norm": 0.8377344012260437, | |
| "learning_rate": 1.1410817433922633e-05, | |
| "loss": 0.7555, | |
| "step": 4175 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "grad_norm": 0.7936707735061646, | |
| "learning_rate": 1.1279537896026606e-05, | |
| "loss": 0.7285, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "grad_norm": 0.9590585231781006, | |
| "learning_rate": 1.114825835813058e-05, | |
| "loss": 0.7239, | |
| "step": 4225 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "grad_norm": 0.9101057648658752, | |
| "learning_rate": 1.1016978820234552e-05, | |
| "loss": 0.755, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "grad_norm": 0.8772357106208801, | |
| "learning_rate": 1.0885699282338526e-05, | |
| "loss": 0.7154, | |
| "step": 4275 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "grad_norm": 0.8619498610496521, | |
| "learning_rate": 1.07544197444425e-05, | |
| "loss": 0.7231, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "grad_norm": 0.8514516353607178, | |
| "learning_rate": 1.0623140206546475e-05, | |
| "loss": 0.7426, | |
| "step": 4325 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "grad_norm": 0.8754194974899292, | |
| "learning_rate": 1.0491860668650445e-05, | |
| "loss": 0.7552, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "grad_norm": 0.8537304997444153, | |
| "learning_rate": 1.036058113075442e-05, | |
| "loss": 0.7414, | |
| "step": 4375 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "grad_norm": 0.8096929788589478, | |
| "learning_rate": 1.0229301592858394e-05, | |
| "loss": 0.7555, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "grad_norm": 0.9001064300537109, | |
| "learning_rate": 1.0098022054962368e-05, | |
| "loss": 0.7485, | |
| "step": 4425 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "grad_norm": 0.9434337019920349, | |
| "learning_rate": 9.96674251706634e-06, | |
| "loss": 0.7263, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "grad_norm": 0.8765788078308105, | |
| "learning_rate": 9.835462979170314e-06, | |
| "loss": 0.7512, | |
| "step": 4475 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "grad_norm": 0.7964215278625488, | |
| "learning_rate": 9.704183441274287e-06, | |
| "loss": 0.7276, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "grad_norm": 0.7790128588676453, | |
| "learning_rate": 9.57290390337826e-06, | |
| "loss": 0.7731, | |
| "step": 4525 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "grad_norm": 0.8012252449989319, | |
| "learning_rate": 9.441624365482233e-06, | |
| "loss": 0.7123, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "grad_norm": 0.9006531238555908, | |
| "learning_rate": 9.310344827586207e-06, | |
| "loss": 0.7267, | |
| "step": 4575 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "grad_norm": 0.8349692821502686, | |
| "learning_rate": 9.179065289690182e-06, | |
| "loss": 0.7815, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "grad_norm": 0.8102928400039673, | |
| "learning_rate": 9.047785751794152e-06, | |
| "loss": 0.7022, | |
| "step": 4625 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "grad_norm": 0.8270648717880249, | |
| "learning_rate": 8.916506213898126e-06, | |
| "loss": 0.7155, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "grad_norm": 0.901828944683075, | |
| "learning_rate": 8.7852266760021e-06, | |
| "loss": 0.7353, | |
| "step": 4675 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "grad_norm": 0.8448766469955444, | |
| "learning_rate": 8.653947138106075e-06, | |
| "loss": 0.7427, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "grad_norm": 0.9027690291404724, | |
| "learning_rate": 8.522667600210047e-06, | |
| "loss": 0.7498, | |
| "step": 4725 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "grad_norm": 0.8727796077728271, | |
| "learning_rate": 8.391388062314021e-06, | |
| "loss": 0.7186, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "grad_norm": 0.8412611484527588, | |
| "learning_rate": 8.260108524417994e-06, | |
| "loss": 0.7088, | |
| "step": 4775 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "grad_norm": 0.822242259979248, | |
| "learning_rate": 8.128828986521968e-06, | |
| "loss": 0.731, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 4.56, | |
| "grad_norm": 0.8580783009529114, | |
| "learning_rate": 7.99754944862594e-06, | |
| "loss": 0.76, | |
| "step": 4825 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "grad_norm": 0.8335314393043518, | |
| "learning_rate": 7.866269910729914e-06, | |
| "loss": 0.7565, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "grad_norm": 0.9883183240890503, | |
| "learning_rate": 7.734990372833889e-06, | |
| "loss": 0.73, | |
| "step": 4875 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "grad_norm": 0.8578433990478516, | |
| "learning_rate": 7.603710834937862e-06, | |
| "loss": 0.7178, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "grad_norm": 0.8443204164505005, | |
| "learning_rate": 7.472431297041835e-06, | |
| "loss": 0.7331, | |
| "step": 4925 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "grad_norm": 0.8731228113174438, | |
| "learning_rate": 7.3411517591458075e-06, | |
| "loss": 0.7395, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "grad_norm": 0.8685081601142883, | |
| "learning_rate": 7.209872221249782e-06, | |
| "loss": 0.7429, | |
| "step": 4975 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "grad_norm": 0.849574625492096, | |
| "learning_rate": 7.078592683353755e-06, | |
| "loss": 0.7477, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "grad_norm": 0.902864396572113, | |
| "learning_rate": 6.947313145457728e-06, | |
| "loss": 0.7447, | |
| "step": 5025 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "grad_norm": 0.8804737329483032, | |
| "learning_rate": 6.8160336075617015e-06, | |
| "loss": 0.7229, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "grad_norm": 0.9037989377975464, | |
| "learning_rate": 6.684754069665676e-06, | |
| "loss": 0.7626, | |
| "step": 5075 | |
| }, | |
| { | |
| "epoch": 4.82, | |
| "grad_norm": 0.9347764849662781, | |
| "learning_rate": 6.553474531769648e-06, | |
| "loss": 0.7505, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "grad_norm": 0.7910996675491333, | |
| "learning_rate": 6.422194993873622e-06, | |
| "loss": 0.7259, | |
| "step": 5125 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "grad_norm": 0.912019670009613, | |
| "learning_rate": 6.290915455977595e-06, | |
| "loss": 0.7319, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "grad_norm": 0.9191232919692993, | |
| "learning_rate": 6.159635918081569e-06, | |
| "loss": 0.7356, | |
| "step": 5175 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "grad_norm": 0.8757007122039795, | |
| "learning_rate": 6.028356380185542e-06, | |
| "loss": 0.732, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "grad_norm": 0.8221475481987, | |
| "learning_rate": 5.897076842289515e-06, | |
| "loss": 0.6988, | |
| "step": 5225 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "grad_norm": 0.8426682949066162, | |
| "learning_rate": 5.765797304393489e-06, | |
| "loss": 0.7385, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 4.98, | |
| "grad_norm": 0.8677511215209961, | |
| "learning_rate": 5.634517766497462e-06, | |
| "loss": 0.7276, | |
| "step": 5275 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "grad_norm": 0.8274013996124268, | |
| "learning_rate": 5.503238228601435e-06, | |
| "loss": 0.7247, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "grad_norm": 0.8982018828392029, | |
| "learning_rate": 5.3719586907054085e-06, | |
| "loss": 0.7201, | |
| "step": 5325 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "grad_norm": 0.8524619340896606, | |
| "learning_rate": 5.240679152809383e-06, | |
| "loss": 0.7283, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 5.08, | |
| "grad_norm": 0.873533308506012, | |
| "learning_rate": 5.109399614913355e-06, | |
| "loss": 0.7264, | |
| "step": 5375 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "grad_norm": 0.8456885814666748, | |
| "learning_rate": 4.978120077017329e-06, | |
| "loss": 0.7224, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "grad_norm": 0.8955851793289185, | |
| "learning_rate": 4.8468405391213024e-06, | |
| "loss": 0.7344, | |
| "step": 5425 | |
| }, | |
| { | |
| "epoch": 5.15, | |
| "grad_norm": 0.8928526639938354, | |
| "learning_rate": 4.715561001225276e-06, | |
| "loss": 0.7368, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "grad_norm": 0.8710963129997253, | |
| "learning_rate": 4.584281463329249e-06, | |
| "loss": 0.757, | |
| "step": 5475 | |
| }, | |
| { | |
| "epoch": 5.19, | |
| "grad_norm": 0.9394299387931824, | |
| "learning_rate": 4.453001925433223e-06, | |
| "loss": 0.7283, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "grad_norm": 0.9365102052688599, | |
| "learning_rate": 4.3217223875371956e-06, | |
| "loss": 0.7294, | |
| "step": 5525 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "grad_norm": 0.8301792740821838, | |
| "learning_rate": 4.19044284964117e-06, | |
| "loss": 0.7362, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "grad_norm": 0.8896806240081787, | |
| "learning_rate": 4.059163311745142e-06, | |
| "loss": 0.7358, | |
| "step": 5575 | |
| }, | |
| { | |
| "epoch": 5.29, | |
| "grad_norm": 0.9053913354873657, | |
| "learning_rate": 3.927883773849116e-06, | |
| "loss": 0.755, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 5.31, | |
| "grad_norm": 0.9083183407783508, | |
| "learning_rate": 3.79660423595309e-06, | |
| "loss": 0.7463, | |
| "step": 5625 | |
| }, | |
| { | |
| "epoch": 5.34, | |
| "grad_norm": 0.9348452091217041, | |
| "learning_rate": 3.6653246980570632e-06, | |
| "loss": 0.727, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 5.36, | |
| "grad_norm": 0.8955479264259338, | |
| "learning_rate": 3.534045160161036e-06, | |
| "loss": 0.7438, | |
| "step": 5675 | |
| }, | |
| { | |
| "epoch": 5.38, | |
| "grad_norm": 0.9147844910621643, | |
| "learning_rate": 3.4027656222650094e-06, | |
| "loss": 0.7224, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "grad_norm": 0.9772645235061646, | |
| "learning_rate": 3.271486084368983e-06, | |
| "loss": 0.7523, | |
| "step": 5725 | |
| }, | |
| { | |
| "epoch": 5.43, | |
| "grad_norm": 0.8953329920768738, | |
| "learning_rate": 3.1402065464729564e-06, | |
| "loss": 0.7247, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "grad_norm": 0.8330567479133606, | |
| "learning_rate": 3.0089270085769296e-06, | |
| "loss": 0.7132, | |
| "step": 5775 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "grad_norm": 0.9282602667808533, | |
| "learning_rate": 2.8776474706809033e-06, | |
| "loss": 0.7399, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 5.5, | |
| "grad_norm": 0.9033696055412292, | |
| "learning_rate": 2.7463679327848766e-06, | |
| "loss": 0.735, | |
| "step": 5825 | |
| }, | |
| { | |
| "epoch": 5.53, | |
| "grad_norm": 0.9616188406944275, | |
| "learning_rate": 2.61508839488885e-06, | |
| "loss": 0.7329, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 5.55, | |
| "grad_norm": 0.863400936126709, | |
| "learning_rate": 2.483808856992823e-06, | |
| "loss": 0.7611, | |
| "step": 5875 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "grad_norm": 0.8783301711082458, | |
| "learning_rate": 2.352529319096797e-06, | |
| "loss": 0.6993, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "grad_norm": 0.8729863166809082, | |
| "learning_rate": 2.22124978120077e-06, | |
| "loss": 0.7058, | |
| "step": 5925 | |
| }, | |
| { | |
| "epoch": 5.62, | |
| "grad_norm": 0.8404456377029419, | |
| "learning_rate": 2.095221424820585e-06, | |
| "loss": 0.7172, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 5.64, | |
| "grad_norm": 0.8831392526626587, | |
| "learning_rate": 1.963941886924558e-06, | |
| "loss": 0.7216, | |
| "step": 5975 | |
| }, | |
| { | |
| "epoch": 5.67, | |
| "grad_norm": 0.8616348505020142, | |
| "learning_rate": 1.8326623490285316e-06, | |
| "loss": 0.7412, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 5.69, | |
| "grad_norm": 0.9031267166137695, | |
| "learning_rate": 1.7013828111325047e-06, | |
| "loss": 0.7245, | |
| "step": 6025 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "grad_norm": 0.8461517691612244, | |
| "learning_rate": 1.5701032732364782e-06, | |
| "loss": 0.7148, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 5.74, | |
| "grad_norm": 0.8163701891899109, | |
| "learning_rate": 1.4388237353404517e-06, | |
| "loss": 0.6964, | |
| "step": 6075 | |
| }, | |
| { | |
| "epoch": 5.76, | |
| "grad_norm": 0.8187835216522217, | |
| "learning_rate": 1.307544197444425e-06, | |
| "loss": 0.7143, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "grad_norm": 0.8065425157546997, | |
| "learning_rate": 1.1762646595483984e-06, | |
| "loss": 0.6912, | |
| "step": 6125 | |
| }, | |
| { | |
| "epoch": 5.81, | |
| "grad_norm": 0.9366108179092407, | |
| "learning_rate": 1.0449851216523717e-06, | |
| "loss": 0.7214, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 5.83, | |
| "grad_norm": 0.8997251391410828, | |
| "learning_rate": 9.137055837563452e-07, | |
| "loss": 0.7478, | |
| "step": 6175 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "grad_norm": 0.8792877197265625, | |
| "learning_rate": 7.824260458603186e-07, | |
| "loss": 0.74, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 5.88, | |
| "grad_norm": 0.8877577185630798, | |
| "learning_rate": 6.51146507964292e-07, | |
| "loss": 0.7186, | |
| "step": 6225 | |
| }, | |
| { | |
| "epoch": 5.9, | |
| "grad_norm": 0.8192344307899475, | |
| "learning_rate": 5.198669700682654e-07, | |
| "loss": 0.7578, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "grad_norm": 0.9072625041007996, | |
| "learning_rate": 3.8858743217223877e-07, | |
| "loss": 0.7066, | |
| "step": 6275 | |
| }, | |
| { | |
| "epoch": 5.95, | |
| "grad_norm": 0.831196665763855, | |
| "learning_rate": 2.5730789427621215e-07, | |
| "loss": 0.7467, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 5.97, | |
| "grad_norm": 0.9208534359931946, | |
| "learning_rate": 1.2602835638018557e-07, | |
| "loss": 0.7377, | |
| "step": 6325 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 6348, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "save_steps": 500, | |
| "total_flos": 1.1235523741876224e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |