{ "best_metric": 0.14961867034435272, "best_model_checkpoint": "/home/ubuntu/ML/source_code/fine-tuned-legalroberta/qa/checkpoint-364860", "epoch": 2.0, "global_step": 364860, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 1.9981728151437082e-05, "loss": 0.3901, "step": 500 }, { "epoch": 0.01, "learning_rate": 1.9963456302874163e-05, "loss": 0.1441, "step": 1000 }, { "epoch": 0.01, "learning_rate": 1.9945184454311244e-05, "loss": 0.107, "step": 1500 }, { "epoch": 0.01, "learning_rate": 1.9926912605748324e-05, "loss": 0.1122, "step": 2000 }, { "epoch": 0.01, "learning_rate": 1.9908640757185405e-05, "loss": 0.1177, "step": 2500 }, { "epoch": 0.02, "learning_rate": 1.9890368908622486e-05, "loss": 0.1039, "step": 3000 }, { "epoch": 0.02, "learning_rate": 1.9872097060059567e-05, "loss": 0.0989, "step": 3500 }, { "epoch": 0.02, "learning_rate": 1.985382521149665e-05, "loss": 0.1081, "step": 4000 }, { "epoch": 0.02, "learning_rate": 1.983555336293373e-05, "loss": 0.0978, "step": 4500 }, { "epoch": 0.03, "learning_rate": 1.981728151437081e-05, "loss": 0.0979, "step": 5000 }, { "epoch": 0.03, "learning_rate": 1.9799009665807893e-05, "loss": 0.1083, "step": 5500 }, { "epoch": 0.03, "learning_rate": 1.9780737817244973e-05, "loss": 0.0935, "step": 6000 }, { "epoch": 0.04, "learning_rate": 1.9762465968682054e-05, "loss": 0.091, "step": 6500 }, { "epoch": 0.04, "learning_rate": 1.9744194120119135e-05, "loss": 0.1068, "step": 7000 }, { "epoch": 0.04, "learning_rate": 1.9725922271556216e-05, "loss": 0.1264, "step": 7500 }, { "epoch": 0.04, "learning_rate": 1.9707650422993296e-05, "loss": 0.1381, "step": 8000 }, { "epoch": 0.05, "learning_rate": 1.9689378574430377e-05, "loss": 0.0971, "step": 8500 }, { "epoch": 0.05, "learning_rate": 1.9671106725867458e-05, "loss": 0.1426, "step": 9000 }, { "epoch": 0.05, "learning_rate": 1.965283487730454e-05, "loss": 0.1167, "step": 9500 }, { "epoch": 0.05, "learning_rate": 1.963456302874162e-05, "loss": 0.1031, "step": 10000 }, { "epoch": 0.06, "learning_rate": 1.96162911801787e-05, "loss": 0.1154, "step": 10500 }, { "epoch": 0.06, "learning_rate": 1.959801933161578e-05, "loss": 0.1116, "step": 11000 }, { "epoch": 0.06, "learning_rate": 1.957974748305286e-05, "loss": 0.0929, "step": 11500 }, { "epoch": 0.07, "learning_rate": 1.9561475634489945e-05, "loss": 0.0812, "step": 12000 }, { "epoch": 0.07, "learning_rate": 1.9543203785927023e-05, "loss": 0.1107, "step": 12500 }, { "epoch": 0.07, "learning_rate": 1.9524931937364103e-05, "loss": 0.0934, "step": 13000 }, { "epoch": 0.07, "learning_rate": 1.9506660088801187e-05, "loss": 0.0963, "step": 13500 }, { "epoch": 0.08, "learning_rate": 1.9488388240238268e-05, "loss": 0.1121, "step": 14000 }, { "epoch": 0.08, "learning_rate": 1.9470116391675345e-05, "loss": 0.1094, "step": 14500 }, { "epoch": 0.08, "learning_rate": 1.945184454311243e-05, "loss": 0.0955, "step": 15000 }, { "epoch": 0.08, "learning_rate": 1.943357269454951e-05, "loss": 0.1061, "step": 15500 }, { "epoch": 0.09, "learning_rate": 1.941530084598659e-05, "loss": 0.1049, "step": 16000 }, { "epoch": 0.09, "learning_rate": 1.939702899742367e-05, "loss": 0.1018, "step": 16500 }, { "epoch": 0.09, "learning_rate": 1.9378757148860752e-05, "loss": 0.1117, "step": 17000 }, { "epoch": 0.1, "learning_rate": 1.9360485300297833e-05, "loss": 0.0995, "step": 17500 }, { "epoch": 0.1, "learning_rate": 1.9342213451734914e-05, "loss": 0.1019, "step": 18000 }, { "epoch": 0.1, "learning_rate": 1.9323941603171994e-05, "loss": 0.0892, "step": 18500 }, { "epoch": 0.1, "learning_rate": 1.9305669754609075e-05, "loss": 0.0982, "step": 19000 }, { "epoch": 0.11, "learning_rate": 1.9287397906046156e-05, "loss": 0.0943, "step": 19500 }, { "epoch": 0.11, "learning_rate": 1.9269126057483236e-05, "loss": 0.0885, "step": 20000 }, { "epoch": 0.11, "learning_rate": 1.9250854208920317e-05, "loss": 0.0956, "step": 20500 }, { "epoch": 0.12, "learning_rate": 1.9232582360357398e-05, "loss": 0.1101, "step": 21000 }, { "epoch": 0.12, "learning_rate": 1.9214310511794482e-05, "loss": 0.099, "step": 21500 }, { "epoch": 0.12, "learning_rate": 1.919603866323156e-05, "loss": 0.0919, "step": 22000 }, { "epoch": 0.12, "learning_rate": 1.917776681466864e-05, "loss": 0.0944, "step": 22500 }, { "epoch": 0.13, "learning_rate": 1.9159494966105724e-05, "loss": 0.1062, "step": 23000 }, { "epoch": 0.13, "learning_rate": 1.9141223117542805e-05, "loss": 0.0833, "step": 23500 }, { "epoch": 0.13, "learning_rate": 1.9122951268979882e-05, "loss": 0.1055, "step": 24000 }, { "epoch": 0.13, "learning_rate": 1.9104679420416966e-05, "loss": 0.0978, "step": 24500 }, { "epoch": 0.14, "learning_rate": 1.9086407571854047e-05, "loss": 0.0844, "step": 25000 }, { "epoch": 0.14, "learning_rate": 1.9068135723291127e-05, "loss": 0.092, "step": 25500 }, { "epoch": 0.14, "learning_rate": 1.9049863874728208e-05, "loss": 0.1131, "step": 26000 }, { "epoch": 0.15, "learning_rate": 1.903159202616529e-05, "loss": 0.0858, "step": 26500 }, { "epoch": 0.15, "learning_rate": 1.901332017760237e-05, "loss": 0.093, "step": 27000 }, { "epoch": 0.15, "learning_rate": 1.899504832903945e-05, "loss": 0.086, "step": 27500 }, { "epoch": 0.15, "learning_rate": 1.897677648047653e-05, "loss": 0.0785, "step": 28000 }, { "epoch": 0.16, "learning_rate": 1.895850463191361e-05, "loss": 0.0949, "step": 28500 }, { "epoch": 0.16, "learning_rate": 1.8940232783350692e-05, "loss": 0.1032, "step": 29000 }, { "epoch": 0.16, "learning_rate": 1.8921960934787773e-05, "loss": 0.0887, "step": 29500 }, { "epoch": 0.16, "learning_rate": 1.8903689086224854e-05, "loss": 0.102, "step": 30000 }, { "epoch": 0.17, "learning_rate": 1.8885417237661934e-05, "loss": 0.099, "step": 30500 }, { "epoch": 0.17, "learning_rate": 1.886714538909902e-05, "loss": 0.0886, "step": 31000 }, { "epoch": 0.17, "learning_rate": 1.8848873540536096e-05, "loss": 0.0955, "step": 31500 }, { "epoch": 0.18, "learning_rate": 1.8830601691973177e-05, "loss": 0.0786, "step": 32000 }, { "epoch": 0.18, "learning_rate": 1.881232984341026e-05, "loss": 0.109, "step": 32500 }, { "epoch": 0.18, "learning_rate": 1.879405799484734e-05, "loss": 0.0798, "step": 33000 }, { "epoch": 0.18, "learning_rate": 1.8775786146284422e-05, "loss": 0.075, "step": 33500 }, { "epoch": 0.19, "learning_rate": 1.8757514297721503e-05, "loss": 0.1025, "step": 34000 }, { "epoch": 0.19, "learning_rate": 1.8739242449158583e-05, "loss": 0.0832, "step": 34500 }, { "epoch": 0.19, "learning_rate": 1.8720970600595664e-05, "loss": 0.0942, "step": 35000 }, { "epoch": 0.19, "learning_rate": 1.8702698752032745e-05, "loss": 0.0905, "step": 35500 }, { "epoch": 0.2, "learning_rate": 1.8684426903469826e-05, "loss": 0.0967, "step": 36000 }, { "epoch": 0.2, "learning_rate": 1.8666155054906906e-05, "loss": 0.1022, "step": 36500 }, { "epoch": 0.2, "learning_rate": 1.8647883206343987e-05, "loss": 0.091, "step": 37000 }, { "epoch": 0.21, "learning_rate": 1.8629611357781068e-05, "loss": 0.1029, "step": 37500 }, { "epoch": 0.21, "learning_rate": 1.861133950921815e-05, "loss": 0.0867, "step": 38000 }, { "epoch": 0.21, "learning_rate": 1.8593067660655232e-05, "loss": 0.1072, "step": 38500 }, { "epoch": 0.21, "learning_rate": 1.857479581209231e-05, "loss": 0.1039, "step": 39000 }, { "epoch": 0.22, "learning_rate": 1.855652396352939e-05, "loss": 0.0988, "step": 39500 }, { "epoch": 0.22, "learning_rate": 1.8538252114966475e-05, "loss": 0.0769, "step": 40000 }, { "epoch": 0.22, "learning_rate": 1.8519980266403555e-05, "loss": 0.0818, "step": 40500 }, { "epoch": 0.22, "learning_rate": 1.8501708417840633e-05, "loss": 0.1, "step": 41000 }, { "epoch": 0.23, "learning_rate": 1.8483436569277717e-05, "loss": 0.1093, "step": 41500 }, { "epoch": 0.23, "learning_rate": 1.8465164720714797e-05, "loss": 0.0806, "step": 42000 }, { "epoch": 0.23, "learning_rate": 1.8446892872151878e-05, "loss": 0.0877, "step": 42500 }, { "epoch": 0.24, "learning_rate": 1.842862102358896e-05, "loss": 0.1024, "step": 43000 }, { "epoch": 0.24, "learning_rate": 1.841034917502604e-05, "loss": 0.0899, "step": 43500 }, { "epoch": 0.24, "learning_rate": 1.839207732646312e-05, "loss": 0.0768, "step": 44000 }, { "epoch": 0.24, "learning_rate": 1.83738054779002e-05, "loss": 0.0896, "step": 44500 }, { "epoch": 0.25, "learning_rate": 1.835553362933728e-05, "loss": 0.0875, "step": 45000 }, { "epoch": 0.25, "learning_rate": 1.8337261780774362e-05, "loss": 0.0855, "step": 45500 }, { "epoch": 0.25, "learning_rate": 1.8318989932211443e-05, "loss": 0.1109, "step": 46000 }, { "epoch": 0.25, "learning_rate": 1.8300718083648524e-05, "loss": 0.0956, "step": 46500 }, { "epoch": 0.26, "learning_rate": 1.8282446235085604e-05, "loss": 0.0936, "step": 47000 }, { "epoch": 0.26, "learning_rate": 1.8264174386522685e-05, "loss": 0.0734, "step": 47500 }, { "epoch": 0.26, "learning_rate": 1.824590253795977e-05, "loss": 0.0805, "step": 48000 }, { "epoch": 0.27, "learning_rate": 1.8227630689396846e-05, "loss": 0.106, "step": 48500 }, { "epoch": 0.27, "learning_rate": 1.8209358840833927e-05, "loss": 0.0693, "step": 49000 }, { "epoch": 0.27, "learning_rate": 1.819108699227101e-05, "loss": 0.0893, "step": 49500 }, { "epoch": 0.27, "learning_rate": 1.8172815143708092e-05, "loss": 0.096, "step": 50000 }, { "epoch": 0.28, "learning_rate": 1.815454329514517e-05, "loss": 0.0879, "step": 50500 }, { "epoch": 0.28, "learning_rate": 1.8136271446582253e-05, "loss": 0.0934, "step": 51000 }, { "epoch": 0.28, "learning_rate": 1.8117999598019334e-05, "loss": 0.0797, "step": 51500 }, { "epoch": 0.29, "learning_rate": 1.8099727749456415e-05, "loss": 0.0825, "step": 52000 }, { "epoch": 0.29, "learning_rate": 1.8081455900893495e-05, "loss": 0.0926, "step": 52500 }, { "epoch": 0.29, "learning_rate": 1.8063184052330576e-05, "loss": 0.0796, "step": 53000 }, { "epoch": 0.29, "learning_rate": 1.8044912203767657e-05, "loss": 0.0604, "step": 53500 }, { "epoch": 0.3, "learning_rate": 1.8026640355204737e-05, "loss": 0.0844, "step": 54000 }, { "epoch": 0.3, "learning_rate": 1.8008368506641818e-05, "loss": 0.0701, "step": 54500 }, { "epoch": 0.3, "learning_rate": 1.79900966580789e-05, "loss": 0.0764, "step": 55000 }, { "epoch": 0.3, "learning_rate": 1.797182480951598e-05, "loss": 0.0856, "step": 55500 }, { "epoch": 0.31, "learning_rate": 1.795355296095306e-05, "loss": 0.0933, "step": 56000 }, { "epoch": 0.31, "learning_rate": 1.793528111239014e-05, "loss": 0.0891, "step": 56500 }, { "epoch": 0.31, "learning_rate": 1.791700926382722e-05, "loss": 0.0736, "step": 57000 }, { "epoch": 0.32, "learning_rate": 1.7898737415264306e-05, "loss": 0.0875, "step": 57500 }, { "epoch": 0.32, "learning_rate": 1.7880465566701383e-05, "loss": 0.0802, "step": 58000 }, { "epoch": 0.32, "learning_rate": 1.7862193718138464e-05, "loss": 0.0759, "step": 58500 }, { "epoch": 0.32, "learning_rate": 1.7843921869575548e-05, "loss": 0.0957, "step": 59000 }, { "epoch": 0.33, "learning_rate": 1.782565002101263e-05, "loss": 0.0853, "step": 59500 }, { "epoch": 0.33, "learning_rate": 1.7807378172449706e-05, "loss": 0.0829, "step": 60000 }, { "epoch": 0.33, "learning_rate": 1.778910632388679e-05, "loss": 0.0798, "step": 60500 }, { "epoch": 0.33, "learning_rate": 1.777083447532387e-05, "loss": 0.0881, "step": 61000 }, { "epoch": 0.34, "learning_rate": 1.775256262676095e-05, "loss": 0.0842, "step": 61500 }, { "epoch": 0.34, "learning_rate": 1.7734290778198032e-05, "loss": 0.0722, "step": 62000 }, { "epoch": 0.34, "learning_rate": 1.7716018929635113e-05, "loss": 0.081, "step": 62500 }, { "epoch": 0.35, "learning_rate": 1.7697747081072193e-05, "loss": 0.0696, "step": 63000 }, { "epoch": 0.35, "learning_rate": 1.7679475232509274e-05, "loss": 0.098, "step": 63500 }, { "epoch": 0.35, "learning_rate": 1.7661203383946355e-05, "loss": 0.067, "step": 64000 }, { "epoch": 0.35, "learning_rate": 1.7642931535383436e-05, "loss": 0.0674, "step": 64500 }, { "epoch": 0.36, "learning_rate": 1.7624659686820516e-05, "loss": 0.0803, "step": 65000 }, { "epoch": 0.36, "learning_rate": 1.7606387838257597e-05, "loss": 0.0715, "step": 65500 }, { "epoch": 0.36, "learning_rate": 1.7588115989694678e-05, "loss": 0.0857, "step": 66000 }, { "epoch": 0.36, "learning_rate": 1.756984414113176e-05, "loss": 0.0849, "step": 66500 }, { "epoch": 0.37, "learning_rate": 1.7551572292568842e-05, "loss": 0.08, "step": 67000 }, { "epoch": 0.37, "learning_rate": 1.753330044400592e-05, "loss": 0.0651, "step": 67500 }, { "epoch": 0.37, "learning_rate": 1.7515028595443004e-05, "loss": 0.0664, "step": 68000 }, { "epoch": 0.38, "learning_rate": 1.7496756746880085e-05, "loss": 0.0555, "step": 68500 }, { "epoch": 0.38, "learning_rate": 1.7478484898317165e-05, "loss": 0.0775, "step": 69000 }, { "epoch": 0.38, "learning_rate": 1.7460213049754246e-05, "loss": 0.0731, "step": 69500 }, { "epoch": 0.38, "learning_rate": 1.7441941201191327e-05, "loss": 0.0723, "step": 70000 }, { "epoch": 0.39, "learning_rate": 1.7423669352628407e-05, "loss": 0.0674, "step": 70500 }, { "epoch": 0.39, "learning_rate": 1.7405397504065488e-05, "loss": 0.0636, "step": 71000 }, { "epoch": 0.39, "learning_rate": 1.738712565550257e-05, "loss": 0.0855, "step": 71500 }, { "epoch": 0.39, "learning_rate": 1.736885380693965e-05, "loss": 0.0696, "step": 72000 }, { "epoch": 0.4, "learning_rate": 1.735058195837673e-05, "loss": 0.0647, "step": 72500 }, { "epoch": 0.4, "learning_rate": 1.733231010981381e-05, "loss": 0.0649, "step": 73000 }, { "epoch": 0.4, "learning_rate": 1.731403826125089e-05, "loss": 0.077, "step": 73500 }, { "epoch": 0.41, "learning_rate": 1.7295766412687972e-05, "loss": 0.0663, "step": 74000 }, { "epoch": 0.41, "learning_rate": 1.7277494564125056e-05, "loss": 0.0675, "step": 74500 }, { "epoch": 0.41, "learning_rate": 1.7259222715562134e-05, "loss": 0.0708, "step": 75000 }, { "epoch": 0.41, "learning_rate": 1.7240950866999214e-05, "loss": 0.0805, "step": 75500 }, { "epoch": 0.42, "learning_rate": 1.72226790184363e-05, "loss": 0.0776, "step": 76000 }, { "epoch": 0.42, "learning_rate": 1.720440716987338e-05, "loss": 0.0604, "step": 76500 }, { "epoch": 0.42, "learning_rate": 1.7186135321310456e-05, "loss": 0.0612, "step": 77000 }, { "epoch": 0.42, "learning_rate": 1.716786347274754e-05, "loss": 0.0546, "step": 77500 }, { "epoch": 0.43, "learning_rate": 1.714959162418462e-05, "loss": 0.0753, "step": 78000 }, { "epoch": 0.43, "learning_rate": 1.7131319775621702e-05, "loss": 0.0688, "step": 78500 }, { "epoch": 0.43, "learning_rate": 1.7113047927058783e-05, "loss": 0.0603, "step": 79000 }, { "epoch": 0.44, "learning_rate": 1.7094776078495863e-05, "loss": 0.0679, "step": 79500 }, { "epoch": 0.44, "learning_rate": 1.7076504229932944e-05, "loss": 0.0715, "step": 80000 }, { "epoch": 0.44, "learning_rate": 1.7058232381370025e-05, "loss": 0.0655, "step": 80500 }, { "epoch": 0.44, "learning_rate": 1.7039960532807105e-05, "loss": 0.0744, "step": 81000 }, { "epoch": 0.45, "learning_rate": 1.7021688684244186e-05, "loss": 0.0636, "step": 81500 }, { "epoch": 0.45, "learning_rate": 1.7003416835681267e-05, "loss": 0.0838, "step": 82000 }, { "epoch": 0.45, "learning_rate": 1.6985144987118347e-05, "loss": 0.064, "step": 82500 }, { "epoch": 0.45, "learning_rate": 1.6966873138555428e-05, "loss": 0.0632, "step": 83000 }, { "epoch": 0.46, "learning_rate": 1.694860128999251e-05, "loss": 0.069, "step": 83500 }, { "epoch": 0.46, "learning_rate": 1.6930329441429593e-05, "loss": 0.0617, "step": 84000 }, { "epoch": 0.46, "learning_rate": 1.691205759286667e-05, "loss": 0.0716, "step": 84500 }, { "epoch": 0.47, "learning_rate": 1.689378574430375e-05, "loss": 0.075, "step": 85000 }, { "epoch": 0.47, "learning_rate": 1.6875513895740835e-05, "loss": 0.0729, "step": 85500 }, { "epoch": 0.47, "learning_rate": 1.6857242047177916e-05, "loss": 0.0669, "step": 86000 }, { "epoch": 0.47, "learning_rate": 1.6838970198614993e-05, "loss": 0.0664, "step": 86500 }, { "epoch": 0.48, "learning_rate": 1.6820698350052077e-05, "loss": 0.077, "step": 87000 }, { "epoch": 0.48, "learning_rate": 1.6802426501489158e-05, "loss": 0.0781, "step": 87500 }, { "epoch": 0.48, "learning_rate": 1.678415465292624e-05, "loss": 0.0666, "step": 88000 }, { "epoch": 0.49, "learning_rate": 1.676588280436332e-05, "loss": 0.0657, "step": 88500 }, { "epoch": 0.49, "learning_rate": 1.67476109558004e-05, "loss": 0.0612, "step": 89000 }, { "epoch": 0.49, "learning_rate": 1.672933910723748e-05, "loss": 0.0694, "step": 89500 }, { "epoch": 0.49, "learning_rate": 1.671106725867456e-05, "loss": 0.0671, "step": 90000 }, { "epoch": 0.5, "learning_rate": 1.6692795410111642e-05, "loss": 0.0729, "step": 90500 }, { "epoch": 0.5, "learning_rate": 1.6674523561548723e-05, "loss": 0.0723, "step": 91000 }, { "epoch": 0.5, "learning_rate": 1.6656251712985803e-05, "loss": 0.0777, "step": 91500 }, { "epoch": 0.5, "learning_rate": 1.6637979864422884e-05, "loss": 0.0798, "step": 92000 }, { "epoch": 0.51, "learning_rate": 1.6619708015859965e-05, "loss": 0.0548, "step": 92500 }, { "epoch": 0.51, "learning_rate": 1.6601436167297046e-05, "loss": 0.0646, "step": 93000 }, { "epoch": 0.51, "learning_rate": 1.658316431873413e-05, "loss": 0.0639, "step": 93500 }, { "epoch": 0.52, "learning_rate": 1.6564892470171207e-05, "loss": 0.0529, "step": 94000 }, { "epoch": 0.52, "learning_rate": 1.6546620621608288e-05, "loss": 0.0577, "step": 94500 }, { "epoch": 0.52, "learning_rate": 1.6528348773045372e-05, "loss": 0.0632, "step": 95000 }, { "epoch": 0.52, "learning_rate": 1.6510076924482452e-05, "loss": 0.0463, "step": 95500 }, { "epoch": 0.53, "learning_rate": 1.649180507591953e-05, "loss": 0.0661, "step": 96000 }, { "epoch": 0.53, "learning_rate": 1.6473533227356614e-05, "loss": 0.0742, "step": 96500 }, { "epoch": 0.53, "learning_rate": 1.6455261378793695e-05, "loss": 0.0549, "step": 97000 }, { "epoch": 0.53, "learning_rate": 1.6436989530230775e-05, "loss": 0.064, "step": 97500 }, { "epoch": 0.54, "learning_rate": 1.6418717681667856e-05, "loss": 0.0597, "step": 98000 }, { "epoch": 0.54, "learning_rate": 1.6400445833104937e-05, "loss": 0.0795, "step": 98500 }, { "epoch": 0.54, "learning_rate": 1.6382173984542017e-05, "loss": 0.0658, "step": 99000 }, { "epoch": 0.55, "learning_rate": 1.6363902135979098e-05, "loss": 0.0574, "step": 99500 }, { "epoch": 0.55, "learning_rate": 1.634563028741618e-05, "loss": 0.0641, "step": 100000 }, { "epoch": 0.55, "learning_rate": 1.632735843885326e-05, "loss": 0.0594, "step": 100500 }, { "epoch": 0.55, "learning_rate": 1.630908659029034e-05, "loss": 0.0572, "step": 101000 }, { "epoch": 0.56, "learning_rate": 1.629081474172742e-05, "loss": 0.067, "step": 101500 }, { "epoch": 0.56, "learning_rate": 1.62725428931645e-05, "loss": 0.0617, "step": 102000 }, { "epoch": 0.56, "learning_rate": 1.6254271044601582e-05, "loss": 0.0689, "step": 102500 }, { "epoch": 0.56, "learning_rate": 1.6235999196038666e-05, "loss": 0.0676, "step": 103000 }, { "epoch": 0.57, "learning_rate": 1.6217727347475744e-05, "loss": 0.067, "step": 103500 }, { "epoch": 0.57, "learning_rate": 1.6199455498912828e-05, "loss": 0.0527, "step": 104000 }, { "epoch": 0.57, "learning_rate": 1.618118365034991e-05, "loss": 0.0581, "step": 104500 }, { "epoch": 0.58, "learning_rate": 1.616291180178699e-05, "loss": 0.0647, "step": 105000 }, { "epoch": 0.58, "learning_rate": 1.614463995322407e-05, "loss": 0.0826, "step": 105500 }, { "epoch": 0.58, "learning_rate": 1.612636810466115e-05, "loss": 0.0654, "step": 106000 }, { "epoch": 0.58, "learning_rate": 1.610809625609823e-05, "loss": 0.066, "step": 106500 }, { "epoch": 0.59, "learning_rate": 1.6089824407535312e-05, "loss": 0.056, "step": 107000 }, { "epoch": 0.59, "learning_rate": 1.6071552558972393e-05, "loss": 0.0715, "step": 107500 }, { "epoch": 0.59, "learning_rate": 1.6053280710409473e-05, "loss": 0.0664, "step": 108000 }, { "epoch": 0.59, "learning_rate": 1.6035008861846554e-05, "loss": 0.072, "step": 108500 }, { "epoch": 0.6, "learning_rate": 1.6016737013283635e-05, "loss": 0.065, "step": 109000 }, { "epoch": 0.6, "learning_rate": 1.5998465164720715e-05, "loss": 0.0648, "step": 109500 }, { "epoch": 0.6, "learning_rate": 1.5980193316157796e-05, "loss": 0.0874, "step": 110000 }, { "epoch": 0.61, "learning_rate": 1.596192146759488e-05, "loss": 0.0721, "step": 110500 }, { "epoch": 0.61, "learning_rate": 1.5943649619031958e-05, "loss": 0.0536, "step": 111000 }, { "epoch": 0.61, "learning_rate": 1.5925377770469038e-05, "loss": 0.0591, "step": 111500 }, { "epoch": 0.61, "learning_rate": 1.5907105921906122e-05, "loss": 0.0627, "step": 112000 }, { "epoch": 0.62, "learning_rate": 1.5888834073343203e-05, "loss": 0.0583, "step": 112500 }, { "epoch": 0.62, "learning_rate": 1.587056222478028e-05, "loss": 0.0569, "step": 113000 }, { "epoch": 0.62, "learning_rate": 1.5852290376217364e-05, "loss": 0.0597, "step": 113500 }, { "epoch": 0.62, "learning_rate": 1.5834018527654445e-05, "loss": 0.0672, "step": 114000 }, { "epoch": 0.63, "learning_rate": 1.5815746679091526e-05, "loss": 0.0565, "step": 114500 }, { "epoch": 0.63, "learning_rate": 1.5797474830528606e-05, "loss": 0.053, "step": 115000 }, { "epoch": 0.63, "learning_rate": 1.5779202981965687e-05, "loss": 0.0535, "step": 115500 }, { "epoch": 0.64, "learning_rate": 1.5760931133402768e-05, "loss": 0.0645, "step": 116000 }, { "epoch": 0.64, "learning_rate": 1.574265928483985e-05, "loss": 0.059, "step": 116500 }, { "epoch": 0.64, "learning_rate": 1.572438743627693e-05, "loss": 0.0703, "step": 117000 }, { "epoch": 0.64, "learning_rate": 1.570611558771401e-05, "loss": 0.0471, "step": 117500 }, { "epoch": 0.65, "learning_rate": 1.568784373915109e-05, "loss": 0.044, "step": 118000 }, { "epoch": 0.65, "learning_rate": 1.566957189058817e-05, "loss": 0.0639, "step": 118500 }, { "epoch": 0.65, "learning_rate": 1.5651300042025252e-05, "loss": 0.0551, "step": 119000 }, { "epoch": 0.66, "learning_rate": 1.5633028193462333e-05, "loss": 0.0573, "step": 119500 }, { "epoch": 0.66, "learning_rate": 1.5614756344899417e-05, "loss": 0.0453, "step": 120000 }, { "epoch": 0.66, "learning_rate": 1.5596484496336494e-05, "loss": 0.063, "step": 120500 }, { "epoch": 0.66, "learning_rate": 1.5578212647773575e-05, "loss": 0.0611, "step": 121000 }, { "epoch": 0.67, "learning_rate": 1.555994079921066e-05, "loss": 0.0519, "step": 121500 }, { "epoch": 0.67, "learning_rate": 1.554166895064774e-05, "loss": 0.0636, "step": 122000 }, { "epoch": 0.67, "learning_rate": 1.5523397102084817e-05, "loss": 0.0803, "step": 122500 }, { "epoch": 0.67, "learning_rate": 1.55051252535219e-05, "loss": 0.0626, "step": 123000 }, { "epoch": 0.68, "learning_rate": 1.5486853404958982e-05, "loss": 0.0476, "step": 123500 }, { "epoch": 0.68, "learning_rate": 1.5468581556396062e-05, "loss": 0.0617, "step": 124000 }, { "epoch": 0.68, "learning_rate": 1.5450309707833143e-05, "loss": 0.0524, "step": 124500 }, { "epoch": 0.69, "learning_rate": 1.5432037859270224e-05, "loss": 0.0498, "step": 125000 }, { "epoch": 0.69, "learning_rate": 1.5413766010707305e-05, "loss": 0.0535, "step": 125500 }, { "epoch": 0.69, "learning_rate": 1.5395494162144385e-05, "loss": 0.0497, "step": 126000 }, { "epoch": 0.69, "learning_rate": 1.5377222313581466e-05, "loss": 0.0592, "step": 126500 }, { "epoch": 0.7, "learning_rate": 1.5358950465018547e-05, "loss": 0.0443, "step": 127000 }, { "epoch": 0.7, "learning_rate": 1.5340678616455627e-05, "loss": 0.0547, "step": 127500 }, { "epoch": 0.7, "learning_rate": 1.5322406767892708e-05, "loss": 0.06, "step": 128000 }, { "epoch": 0.7, "learning_rate": 1.530413491932979e-05, "loss": 0.0482, "step": 128500 }, { "epoch": 0.71, "learning_rate": 1.528586307076687e-05, "loss": 0.0559, "step": 129000 }, { "epoch": 0.71, "learning_rate": 1.5267591222203954e-05, "loss": 0.0533, "step": 129500 }, { "epoch": 0.71, "learning_rate": 1.5249319373641031e-05, "loss": 0.0581, "step": 130000 }, { "epoch": 0.72, "learning_rate": 1.5231047525078113e-05, "loss": 0.0615, "step": 130500 }, { "epoch": 0.72, "learning_rate": 1.5212775676515194e-05, "loss": 0.0518, "step": 131000 }, { "epoch": 0.72, "learning_rate": 1.5194503827952276e-05, "loss": 0.0436, "step": 131500 }, { "epoch": 0.72, "learning_rate": 1.5176231979389355e-05, "loss": 0.0558, "step": 132000 }, { "epoch": 0.73, "learning_rate": 1.5157960130826436e-05, "loss": 0.0472, "step": 132500 }, { "epoch": 0.73, "learning_rate": 1.5139688282263518e-05, "loss": 0.0503, "step": 133000 }, { "epoch": 0.73, "learning_rate": 1.5121416433700599e-05, "loss": 0.0482, "step": 133500 }, { "epoch": 0.73, "learning_rate": 1.510314458513768e-05, "loss": 0.0584, "step": 134000 }, { "epoch": 0.74, "learning_rate": 1.508487273657476e-05, "loss": 0.0632, "step": 134500 }, { "epoch": 0.74, "learning_rate": 1.5066600888011841e-05, "loss": 0.0571, "step": 135000 }, { "epoch": 0.74, "learning_rate": 1.5048329039448922e-05, "loss": 0.0524, "step": 135500 }, { "epoch": 0.75, "learning_rate": 1.5030057190886003e-05, "loss": 0.0447, "step": 136000 }, { "epoch": 0.75, "learning_rate": 1.5011785342323083e-05, "loss": 0.0541, "step": 136500 }, { "epoch": 0.75, "learning_rate": 1.4993513493760166e-05, "loss": 0.0487, "step": 137000 }, { "epoch": 0.75, "learning_rate": 1.4975241645197245e-05, "loss": 0.063, "step": 137500 }, { "epoch": 0.76, "learning_rate": 1.4956969796634327e-05, "loss": 0.0576, "step": 138000 }, { "epoch": 0.76, "learning_rate": 1.4938697948071408e-05, "loss": 0.0618, "step": 138500 }, { "epoch": 0.76, "learning_rate": 1.4920426099508489e-05, "loss": 0.0439, "step": 139000 }, { "epoch": 0.76, "learning_rate": 1.490215425094557e-05, "loss": 0.0455, "step": 139500 }, { "epoch": 0.77, "learning_rate": 1.488388240238265e-05, "loss": 0.0581, "step": 140000 }, { "epoch": 0.77, "learning_rate": 1.4865610553819732e-05, "loss": 0.0544, "step": 140500 }, { "epoch": 0.77, "learning_rate": 1.4847338705256813e-05, "loss": 0.0521, "step": 141000 }, { "epoch": 0.78, "learning_rate": 1.4829066856693892e-05, "loss": 0.0454, "step": 141500 }, { "epoch": 0.78, "learning_rate": 1.4810795008130974e-05, "loss": 0.0518, "step": 142000 }, { "epoch": 0.78, "learning_rate": 1.4792523159568055e-05, "loss": 0.0579, "step": 142500 }, { "epoch": 0.78, "learning_rate": 1.4774251311005138e-05, "loss": 0.0357, "step": 143000 }, { "epoch": 0.79, "learning_rate": 1.4755979462442217e-05, "loss": 0.0494, "step": 143500 }, { "epoch": 0.79, "learning_rate": 1.4737707613879297e-05, "loss": 0.0459, "step": 144000 }, { "epoch": 0.79, "learning_rate": 1.471943576531638e-05, "loss": 0.0581, "step": 144500 }, { "epoch": 0.79, "learning_rate": 1.4701163916753459e-05, "loss": 0.0546, "step": 145000 }, { "epoch": 0.8, "learning_rate": 1.468289206819054e-05, "loss": 0.0551, "step": 145500 }, { "epoch": 0.8, "learning_rate": 1.4664620219627622e-05, "loss": 0.0476, "step": 146000 }, { "epoch": 0.8, "learning_rate": 1.4646348371064702e-05, "loss": 0.0533, "step": 146500 }, { "epoch": 0.81, "learning_rate": 1.4628076522501781e-05, "loss": 0.0561, "step": 147000 }, { "epoch": 0.81, "learning_rate": 1.4609804673938864e-05, "loss": 0.0504, "step": 147500 }, { "epoch": 0.81, "learning_rate": 1.4591532825375944e-05, "loss": 0.0398, "step": 148000 }, { "epoch": 0.81, "learning_rate": 1.4573260976813027e-05, "loss": 0.054, "step": 148500 }, { "epoch": 0.82, "learning_rate": 1.4554989128250106e-05, "loss": 0.047, "step": 149000 }, { "epoch": 0.82, "learning_rate": 1.4536717279687187e-05, "loss": 0.047, "step": 149500 }, { "epoch": 0.82, "learning_rate": 1.4518445431124269e-05, "loss": 0.0489, "step": 150000 }, { "epoch": 0.82, "learning_rate": 1.450017358256135e-05, "loss": 0.0551, "step": 150500 }, { "epoch": 0.83, "learning_rate": 1.4481901733998429e-05, "loss": 0.043, "step": 151000 }, { "epoch": 0.83, "learning_rate": 1.4463629885435511e-05, "loss": 0.0451, "step": 151500 }, { "epoch": 0.83, "learning_rate": 1.4445358036872592e-05, "loss": 0.057, "step": 152000 }, { "epoch": 0.84, "learning_rate": 1.4427086188309674e-05, "loss": 0.0554, "step": 152500 }, { "epoch": 0.84, "learning_rate": 1.4408814339746753e-05, "loss": 0.0469, "step": 153000 }, { "epoch": 0.84, "learning_rate": 1.4390542491183834e-05, "loss": 0.0504, "step": 153500 }, { "epoch": 0.84, "learning_rate": 1.4372270642620916e-05, "loss": 0.0567, "step": 154000 }, { "epoch": 0.85, "learning_rate": 1.4353998794057995e-05, "loss": 0.0634, "step": 154500 }, { "epoch": 0.85, "learning_rate": 1.4335726945495076e-05, "loss": 0.0471, "step": 155000 }, { "epoch": 0.85, "learning_rate": 1.4317455096932158e-05, "loss": 0.0391, "step": 155500 }, { "epoch": 0.86, "learning_rate": 1.4299183248369239e-05, "loss": 0.0481, "step": 156000 }, { "epoch": 0.86, "learning_rate": 1.4280911399806318e-05, "loss": 0.0554, "step": 156500 }, { "epoch": 0.86, "learning_rate": 1.42626395512434e-05, "loss": 0.0501, "step": 157000 }, { "epoch": 0.86, "learning_rate": 1.4244367702680481e-05, "loss": 0.0456, "step": 157500 }, { "epoch": 0.87, "learning_rate": 1.4226095854117564e-05, "loss": 0.0331, "step": 158000 }, { "epoch": 0.87, "learning_rate": 1.4207824005554643e-05, "loss": 0.0514, "step": 158500 }, { "epoch": 0.87, "learning_rate": 1.4189552156991723e-05, "loss": 0.0434, "step": 159000 }, { "epoch": 0.87, "learning_rate": 1.4171280308428806e-05, "loss": 0.0519, "step": 159500 }, { "epoch": 0.88, "learning_rate": 1.4153008459865886e-05, "loss": 0.0434, "step": 160000 }, { "epoch": 0.88, "learning_rate": 1.4134736611302965e-05, "loss": 0.0385, "step": 160500 }, { "epoch": 0.88, "learning_rate": 1.4116464762740048e-05, "loss": 0.058, "step": 161000 }, { "epoch": 0.89, "learning_rate": 1.4098192914177128e-05, "loss": 0.0476, "step": 161500 }, { "epoch": 0.89, "learning_rate": 1.4079921065614207e-05, "loss": 0.0462, "step": 162000 }, { "epoch": 0.89, "learning_rate": 1.406164921705129e-05, "loss": 0.0447, "step": 162500 }, { "epoch": 0.89, "learning_rate": 1.404337736848837e-05, "loss": 0.048, "step": 163000 }, { "epoch": 0.9, "learning_rate": 1.4025105519925453e-05, "loss": 0.0442, "step": 163500 }, { "epoch": 0.9, "learning_rate": 1.4006833671362532e-05, "loss": 0.0555, "step": 164000 }, { "epoch": 0.9, "learning_rate": 1.3988561822799613e-05, "loss": 0.0434, "step": 164500 }, { "epoch": 0.9, "learning_rate": 1.3970289974236695e-05, "loss": 0.0577, "step": 165000 }, { "epoch": 0.91, "learning_rate": 1.3952018125673776e-05, "loss": 0.0522, "step": 165500 }, { "epoch": 0.91, "learning_rate": 1.3933746277110855e-05, "loss": 0.0412, "step": 166000 }, { "epoch": 0.91, "learning_rate": 1.3915474428547937e-05, "loss": 0.0601, "step": 166500 }, { "epoch": 0.92, "learning_rate": 1.3897202579985018e-05, "loss": 0.0553, "step": 167000 }, { "epoch": 0.92, "learning_rate": 1.38789307314221e-05, "loss": 0.0522, "step": 167500 }, { "epoch": 0.92, "learning_rate": 1.386065888285918e-05, "loss": 0.0505, "step": 168000 }, { "epoch": 0.92, "learning_rate": 1.384238703429626e-05, "loss": 0.0497, "step": 168500 }, { "epoch": 0.93, "learning_rate": 1.3824115185733342e-05, "loss": 0.0378, "step": 169000 }, { "epoch": 0.93, "learning_rate": 1.3805843337170423e-05, "loss": 0.0399, "step": 169500 }, { "epoch": 0.93, "learning_rate": 1.3787571488607504e-05, "loss": 0.0485, "step": 170000 }, { "epoch": 0.93, "learning_rate": 1.3769299640044584e-05, "loss": 0.0416, "step": 170500 }, { "epoch": 0.94, "learning_rate": 1.3751027791481665e-05, "loss": 0.0486, "step": 171000 }, { "epoch": 0.94, "learning_rate": 1.3732755942918746e-05, "loss": 0.0498, "step": 171500 }, { "epoch": 0.94, "learning_rate": 1.3714484094355827e-05, "loss": 0.0515, "step": 172000 }, { "epoch": 0.95, "learning_rate": 1.3696212245792909e-05, "loss": 0.0403, "step": 172500 }, { "epoch": 0.95, "learning_rate": 1.367794039722999e-05, "loss": 0.0461, "step": 173000 }, { "epoch": 0.95, "learning_rate": 1.3659668548667069e-05, "loss": 0.0557, "step": 173500 }, { "epoch": 0.95, "learning_rate": 1.3641396700104151e-05, "loss": 0.0602, "step": 174000 }, { "epoch": 0.96, "learning_rate": 1.3623124851541232e-05, "loss": 0.0416, "step": 174500 }, { "epoch": 0.96, "learning_rate": 1.3604853002978312e-05, "loss": 0.0472, "step": 175000 }, { "epoch": 0.96, "learning_rate": 1.3586581154415393e-05, "loss": 0.0475, "step": 175500 }, { "epoch": 0.96, "learning_rate": 1.3568309305852474e-05, "loss": 0.0478, "step": 176000 }, { "epoch": 0.97, "learning_rate": 1.3550037457289556e-05, "loss": 0.0448, "step": 176500 }, { "epoch": 0.97, "learning_rate": 1.3531765608726637e-05, "loss": 0.0444, "step": 177000 }, { "epoch": 0.97, "learning_rate": 1.3513493760163716e-05, "loss": 0.0459, "step": 177500 }, { "epoch": 0.98, "learning_rate": 1.3495221911600798e-05, "loss": 0.0381, "step": 178000 }, { "epoch": 0.98, "learning_rate": 1.3476950063037879e-05, "loss": 0.0402, "step": 178500 }, { "epoch": 0.98, "learning_rate": 1.3458678214474961e-05, "loss": 0.0338, "step": 179000 }, { "epoch": 0.98, "learning_rate": 1.344040636591204e-05, "loss": 0.0527, "step": 179500 }, { "epoch": 0.99, "learning_rate": 1.3422134517349121e-05, "loss": 0.0381, "step": 180000 }, { "epoch": 0.99, "learning_rate": 1.3403862668786203e-05, "loss": 0.0473, "step": 180500 }, { "epoch": 0.99, "learning_rate": 1.3385590820223282e-05, "loss": 0.0475, "step": 181000 }, { "epoch": 0.99, "learning_rate": 1.3367318971660363e-05, "loss": 0.0482, "step": 181500 }, { "epoch": 1.0, "learning_rate": 1.3349047123097446e-05, "loss": 0.0432, "step": 182000 }, { "epoch": 1.0, "eval_loss": 0.15653175115585327, "eval_runtime": 1676.2688, "eval_samples_per_second": 138.216, "eval_steps_per_second": 13.822, "step": 182430 }, { "epoch": 1.0, "learning_rate": 1.3330775274534526e-05, "loss": 0.0411, "step": 182500 }, { "epoch": 1.0, "learning_rate": 1.3312503425971605e-05, "loss": 0.0428, "step": 183000 }, { "epoch": 1.01, "learning_rate": 1.3294231577408688e-05, "loss": 0.0454, "step": 183500 }, { "epoch": 1.01, "learning_rate": 1.3275959728845768e-05, "loss": 0.0453, "step": 184000 }, { "epoch": 1.01, "learning_rate": 1.325768788028285e-05, "loss": 0.0451, "step": 184500 }, { "epoch": 1.01, "learning_rate": 1.323941603171993e-05, "loss": 0.0426, "step": 185000 }, { "epoch": 1.02, "learning_rate": 1.322114418315701e-05, "loss": 0.0386, "step": 185500 }, { "epoch": 1.02, "learning_rate": 1.3202872334594093e-05, "loss": 0.0422, "step": 186000 }, { "epoch": 1.02, "learning_rate": 1.3184600486031174e-05, "loss": 0.0491, "step": 186500 }, { "epoch": 1.03, "learning_rate": 1.3166328637468253e-05, "loss": 0.0493, "step": 187000 }, { "epoch": 1.03, "learning_rate": 1.3148056788905335e-05, "loss": 0.0388, "step": 187500 }, { "epoch": 1.03, "learning_rate": 1.3129784940342416e-05, "loss": 0.0429, "step": 188000 }, { "epoch": 1.03, "learning_rate": 1.3111513091779498e-05, "loss": 0.0501, "step": 188500 }, { "epoch": 1.04, "learning_rate": 1.3093241243216577e-05, "loss": 0.0423, "step": 189000 }, { "epoch": 1.04, "learning_rate": 1.3074969394653658e-05, "loss": 0.0458, "step": 189500 }, { "epoch": 1.04, "learning_rate": 1.305669754609074e-05, "loss": 0.0411, "step": 190000 }, { "epoch": 1.04, "learning_rate": 1.303842569752782e-05, "loss": 0.0411, "step": 190500 }, { "epoch": 1.05, "learning_rate": 1.30201538489649e-05, "loss": 0.037, "step": 191000 }, { "epoch": 1.05, "learning_rate": 1.3001882000401982e-05, "loss": 0.039, "step": 191500 }, { "epoch": 1.05, "learning_rate": 1.2983610151839063e-05, "loss": 0.0468, "step": 192000 }, { "epoch": 1.06, "learning_rate": 1.2965338303276142e-05, "loss": 0.0404, "step": 192500 }, { "epoch": 1.06, "learning_rate": 1.2947066454713224e-05, "loss": 0.0394, "step": 193000 }, { "epoch": 1.06, "learning_rate": 1.2928794606150305e-05, "loss": 0.0454, "step": 193500 }, { "epoch": 1.06, "learning_rate": 1.2910522757587387e-05, "loss": 0.0402, "step": 194000 }, { "epoch": 1.07, "learning_rate": 1.2892250909024466e-05, "loss": 0.0507, "step": 194500 }, { "epoch": 1.07, "learning_rate": 1.2873979060461547e-05, "loss": 0.0429, "step": 195000 }, { "epoch": 1.07, "learning_rate": 1.285570721189863e-05, "loss": 0.0452, "step": 195500 }, { "epoch": 1.07, "learning_rate": 1.283743536333571e-05, "loss": 0.042, "step": 196000 }, { "epoch": 1.08, "learning_rate": 1.281916351477279e-05, "loss": 0.0482, "step": 196500 }, { "epoch": 1.08, "learning_rate": 1.2800891666209872e-05, "loss": 0.0457, "step": 197000 }, { "epoch": 1.08, "learning_rate": 1.2782619817646952e-05, "loss": 0.0383, "step": 197500 }, { "epoch": 1.09, "learning_rate": 1.2764347969084031e-05, "loss": 0.0384, "step": 198000 }, { "epoch": 1.09, "learning_rate": 1.2746076120521114e-05, "loss": 0.0558, "step": 198500 }, { "epoch": 1.09, "learning_rate": 1.2727804271958194e-05, "loss": 0.0362, "step": 199000 }, { "epoch": 1.09, "learning_rate": 1.2709532423395277e-05, "loss": 0.044, "step": 199500 }, { "epoch": 1.1, "learning_rate": 1.2691260574832356e-05, "loss": 0.0475, "step": 200000 }, { "epoch": 1.1, "learning_rate": 1.2672988726269437e-05, "loss": 0.0404, "step": 200500 }, { "epoch": 1.1, "learning_rate": 1.2654716877706519e-05, "loss": 0.0384, "step": 201000 }, { "epoch": 1.1, "learning_rate": 1.26364450291436e-05, "loss": 0.0528, "step": 201500 }, { "epoch": 1.11, "learning_rate": 1.261817318058068e-05, "loss": 0.0572, "step": 202000 }, { "epoch": 1.11, "learning_rate": 1.2599901332017761e-05, "loss": 0.0365, "step": 202500 }, { "epoch": 1.11, "learning_rate": 1.2581629483454842e-05, "loss": 0.0354, "step": 203000 }, { "epoch": 1.12, "learning_rate": 1.2563357634891924e-05, "loss": 0.0391, "step": 203500 }, { "epoch": 1.12, "learning_rate": 1.2545085786329003e-05, "loss": 0.0394, "step": 204000 }, { "epoch": 1.12, "learning_rate": 1.2526813937766086e-05, "loss": 0.044, "step": 204500 }, { "epoch": 1.12, "learning_rate": 1.2508542089203166e-05, "loss": 0.0436, "step": 205000 }, { "epoch": 1.13, "learning_rate": 1.2490270240640247e-05, "loss": 0.0294, "step": 205500 }, { "epoch": 1.13, "learning_rate": 1.2471998392077328e-05, "loss": 0.0422, "step": 206000 }, { "epoch": 1.13, "learning_rate": 1.2453726543514408e-05, "loss": 0.0428, "step": 206500 }, { "epoch": 1.13, "learning_rate": 1.2435454694951489e-05, "loss": 0.0414, "step": 207000 }, { "epoch": 1.14, "learning_rate": 1.241718284638857e-05, "loss": 0.0411, "step": 207500 }, { "epoch": 1.14, "learning_rate": 1.239891099782565e-05, "loss": 0.0261, "step": 208000 }, { "epoch": 1.14, "learning_rate": 1.2380639149262733e-05, "loss": 0.0327, "step": 208500 }, { "epoch": 1.15, "learning_rate": 1.2362367300699814e-05, "loss": 0.0373, "step": 209000 }, { "epoch": 1.15, "learning_rate": 1.2344095452136893e-05, "loss": 0.0467, "step": 209500 }, { "epoch": 1.15, "learning_rate": 1.2325823603573975e-05, "loss": 0.0375, "step": 210000 }, { "epoch": 1.15, "learning_rate": 1.2307551755011056e-05, "loss": 0.042, "step": 210500 }, { "epoch": 1.16, "learning_rate": 1.2289279906448138e-05, "loss": 0.0365, "step": 211000 }, { "epoch": 1.16, "learning_rate": 1.2271008057885217e-05, "loss": 0.0464, "step": 211500 }, { "epoch": 1.16, "learning_rate": 1.2252736209322298e-05, "loss": 0.0398, "step": 212000 }, { "epoch": 1.16, "learning_rate": 1.223446436075938e-05, "loss": 0.0391, "step": 212500 }, { "epoch": 1.17, "learning_rate": 1.221619251219646e-05, "loss": 0.0413, "step": 213000 }, { "epoch": 1.17, "learning_rate": 1.219792066363354e-05, "loss": 0.0358, "step": 213500 }, { "epoch": 1.17, "learning_rate": 1.2179648815070622e-05, "loss": 0.043, "step": 214000 }, { "epoch": 1.18, "learning_rate": 1.2161376966507703e-05, "loss": 0.0413, "step": 214500 }, { "epoch": 1.18, "learning_rate": 1.2143105117944785e-05, "loss": 0.0513, "step": 215000 }, { "epoch": 1.18, "learning_rate": 1.2124833269381864e-05, "loss": 0.0421, "step": 215500 }, { "epoch": 1.18, "learning_rate": 1.2106561420818945e-05, "loss": 0.0474, "step": 216000 }, { "epoch": 1.19, "learning_rate": 1.2088289572256027e-05, "loss": 0.0445, "step": 216500 }, { "epoch": 1.19, "learning_rate": 1.2070017723693106e-05, "loss": 0.0396, "step": 217000 }, { "epoch": 1.19, "learning_rate": 1.2051745875130187e-05, "loss": 0.038, "step": 217500 }, { "epoch": 1.19, "learning_rate": 1.203347402656727e-05, "loss": 0.0269, "step": 218000 }, { "epoch": 1.2, "learning_rate": 1.201520217800435e-05, "loss": 0.0422, "step": 218500 }, { "epoch": 1.2, "learning_rate": 1.199693032944143e-05, "loss": 0.0522, "step": 219000 }, { "epoch": 1.2, "learning_rate": 1.1978658480878512e-05, "loss": 0.035, "step": 219500 }, { "epoch": 1.21, "learning_rate": 1.1960386632315592e-05, "loss": 0.0388, "step": 220000 }, { "epoch": 1.21, "learning_rate": 1.1942114783752675e-05, "loss": 0.033, "step": 220500 }, { "epoch": 1.21, "learning_rate": 1.1923842935189754e-05, "loss": 0.0459, "step": 221000 }, { "epoch": 1.21, "learning_rate": 1.1905571086626834e-05, "loss": 0.0368, "step": 221500 }, { "epoch": 1.22, "learning_rate": 1.1887299238063917e-05, "loss": 0.0415, "step": 222000 }, { "epoch": 1.22, "learning_rate": 1.1869027389500997e-05, "loss": 0.0373, "step": 222500 }, { "epoch": 1.22, "learning_rate": 1.1850755540938076e-05, "loss": 0.0308, "step": 223000 }, { "epoch": 1.23, "learning_rate": 1.1832483692375159e-05, "loss": 0.0378, "step": 223500 }, { "epoch": 1.23, "learning_rate": 1.181421184381224e-05, "loss": 0.0424, "step": 224000 }, { "epoch": 1.23, "learning_rate": 1.1795939995249322e-05, "loss": 0.0516, "step": 224500 }, { "epoch": 1.23, "learning_rate": 1.1777668146686401e-05, "loss": 0.0349, "step": 225000 }, { "epoch": 1.24, "learning_rate": 1.1759396298123482e-05, "loss": 0.0281, "step": 225500 }, { "epoch": 1.24, "learning_rate": 1.1741124449560564e-05, "loss": 0.0424, "step": 226000 }, { "epoch": 1.24, "learning_rate": 1.1722852600997643e-05, "loss": 0.033, "step": 226500 }, { "epoch": 1.24, "learning_rate": 1.1704580752434724e-05, "loss": 0.0482, "step": 227000 }, { "epoch": 1.25, "learning_rate": 1.1686308903871806e-05, "loss": 0.0361, "step": 227500 }, { "epoch": 1.25, "learning_rate": 1.1668037055308887e-05, "loss": 0.0392, "step": 228000 }, { "epoch": 1.25, "learning_rate": 1.1649765206745966e-05, "loss": 0.0357, "step": 228500 }, { "epoch": 1.26, "learning_rate": 1.1631493358183048e-05, "loss": 0.0428, "step": 229000 }, { "epoch": 1.26, "learning_rate": 1.1613221509620129e-05, "loss": 0.0337, "step": 229500 }, { "epoch": 1.26, "learning_rate": 1.1594949661057211e-05, "loss": 0.0395, "step": 230000 }, { "epoch": 1.26, "learning_rate": 1.157667781249429e-05, "loss": 0.0376, "step": 230500 }, { "epoch": 1.27, "learning_rate": 1.1558405963931371e-05, "loss": 0.0342, "step": 231000 }, { "epoch": 1.27, "learning_rate": 1.1540134115368453e-05, "loss": 0.0442, "step": 231500 }, { "epoch": 1.27, "learning_rate": 1.1521862266805534e-05, "loss": 0.0445, "step": 232000 }, { "epoch": 1.27, "learning_rate": 1.1503590418242613e-05, "loss": 0.0396, "step": 232500 }, { "epoch": 1.28, "learning_rate": 1.1485318569679696e-05, "loss": 0.039, "step": 233000 }, { "epoch": 1.28, "learning_rate": 1.1467046721116776e-05, "loss": 0.0394, "step": 233500 }, { "epoch": 1.28, "learning_rate": 1.1448774872553857e-05, "loss": 0.0299, "step": 234000 }, { "epoch": 1.29, "learning_rate": 1.1430503023990938e-05, "loss": 0.0251, "step": 234500 }, { "epoch": 1.29, "learning_rate": 1.1412231175428018e-05, "loss": 0.0359, "step": 235000 }, { "epoch": 1.29, "learning_rate": 1.13939593268651e-05, "loss": 0.0364, "step": 235500 }, { "epoch": 1.29, "learning_rate": 1.137568747830218e-05, "loss": 0.0334, "step": 236000 }, { "epoch": 1.3, "learning_rate": 1.135741562973926e-05, "loss": 0.0369, "step": 236500 }, { "epoch": 1.3, "learning_rate": 1.1339143781176343e-05, "loss": 0.0326, "step": 237000 }, { "epoch": 1.3, "learning_rate": 1.1320871932613424e-05, "loss": 0.0429, "step": 237500 }, { "epoch": 1.3, "learning_rate": 1.1302600084050504e-05, "loss": 0.0433, "step": 238000 }, { "epoch": 1.31, "learning_rate": 1.1284328235487585e-05, "loss": 0.0383, "step": 238500 }, { "epoch": 1.31, "learning_rate": 1.1266056386924666e-05, "loss": 0.0335, "step": 239000 }, { "epoch": 1.31, "learning_rate": 1.1247784538361748e-05, "loss": 0.0388, "step": 239500 }, { "epoch": 1.32, "learning_rate": 1.1229512689798827e-05, "loss": 0.0349, "step": 240000 }, { "epoch": 1.32, "learning_rate": 1.121124084123591e-05, "loss": 0.0311, "step": 240500 }, { "epoch": 1.32, "learning_rate": 1.119296899267299e-05, "loss": 0.0453, "step": 241000 }, { "epoch": 1.32, "learning_rate": 1.117469714411007e-05, "loss": 0.0392, "step": 241500 }, { "epoch": 1.33, "learning_rate": 1.1156425295547152e-05, "loss": 0.0429, "step": 242000 }, { "epoch": 1.33, "learning_rate": 1.1138153446984232e-05, "loss": 0.0441, "step": 242500 }, { "epoch": 1.33, "learning_rate": 1.1119881598421315e-05, "loss": 0.0365, "step": 243000 }, { "epoch": 1.33, "learning_rate": 1.1101609749858394e-05, "loss": 0.0374, "step": 243500 }, { "epoch": 1.34, "learning_rate": 1.1083337901295474e-05, "loss": 0.0434, "step": 244000 }, { "epoch": 1.34, "learning_rate": 1.1065066052732557e-05, "loss": 0.0411, "step": 244500 }, { "epoch": 1.34, "learning_rate": 1.1046794204169637e-05, "loss": 0.0409, "step": 245000 }, { "epoch": 1.35, "learning_rate": 1.1028522355606716e-05, "loss": 0.0373, "step": 245500 }, { "epoch": 1.35, "learning_rate": 1.1010250507043799e-05, "loss": 0.0427, "step": 246000 }, { "epoch": 1.35, "learning_rate": 1.099197865848088e-05, "loss": 0.0351, "step": 246500 }, { "epoch": 1.35, "learning_rate": 1.0973706809917962e-05, "loss": 0.0285, "step": 247000 }, { "epoch": 1.36, "learning_rate": 1.0955434961355041e-05, "loss": 0.0364, "step": 247500 }, { "epoch": 1.36, "learning_rate": 1.0937163112792122e-05, "loss": 0.0448, "step": 248000 }, { "epoch": 1.36, "learning_rate": 1.0918891264229204e-05, "loss": 0.0333, "step": 248500 }, { "epoch": 1.36, "learning_rate": 1.0900619415666285e-05, "loss": 0.0427, "step": 249000 }, { "epoch": 1.37, "learning_rate": 1.0882347567103364e-05, "loss": 0.0393, "step": 249500 }, { "epoch": 1.37, "learning_rate": 1.0864075718540446e-05, "loss": 0.0413, "step": 250000 }, { "epoch": 1.37, "learning_rate": 1.0845803869977527e-05, "loss": 0.0322, "step": 250500 }, { "epoch": 1.38, "learning_rate": 1.082753202141461e-05, "loss": 0.0341, "step": 251000 }, { "epoch": 1.38, "learning_rate": 1.0809260172851688e-05, "loss": 0.0363, "step": 251500 }, { "epoch": 1.38, "learning_rate": 1.0790988324288769e-05, "loss": 0.0316, "step": 252000 }, { "epoch": 1.38, "learning_rate": 1.0772716475725851e-05, "loss": 0.0393, "step": 252500 }, { "epoch": 1.39, "learning_rate": 1.075444462716293e-05, "loss": 0.0328, "step": 253000 }, { "epoch": 1.39, "learning_rate": 1.0736172778600011e-05, "loss": 0.0354, "step": 253500 }, { "epoch": 1.39, "learning_rate": 1.0717900930037093e-05, "loss": 0.03, "step": 254000 }, { "epoch": 1.4, "learning_rate": 1.0699629081474174e-05, "loss": 0.0423, "step": 254500 }, { "epoch": 1.4, "learning_rate": 1.0681357232911253e-05, "loss": 0.04, "step": 255000 }, { "epoch": 1.4, "learning_rate": 1.0663085384348335e-05, "loss": 0.029, "step": 255500 }, { "epoch": 1.4, "learning_rate": 1.0644813535785416e-05, "loss": 0.039, "step": 256000 }, { "epoch": 1.41, "learning_rate": 1.0626541687222499e-05, "loss": 0.0335, "step": 256500 }, { "epoch": 1.41, "learning_rate": 1.0608269838659578e-05, "loss": 0.0317, "step": 257000 }, { "epoch": 1.41, "learning_rate": 1.0589997990096658e-05, "loss": 0.0515, "step": 257500 }, { "epoch": 1.41, "learning_rate": 1.057172614153374e-05, "loss": 0.0376, "step": 258000 }, { "epoch": 1.42, "learning_rate": 1.0553454292970821e-05, "loss": 0.0413, "step": 258500 }, { "epoch": 1.42, "learning_rate": 1.05351824444079e-05, "loss": 0.0363, "step": 259000 }, { "epoch": 1.42, "learning_rate": 1.0516910595844983e-05, "loss": 0.0336, "step": 259500 }, { "epoch": 1.43, "learning_rate": 1.0498638747282063e-05, "loss": 0.0405, "step": 260000 }, { "epoch": 1.43, "learning_rate": 1.0480366898719146e-05, "loss": 0.042, "step": 260500 }, { "epoch": 1.43, "learning_rate": 1.0462095050156225e-05, "loss": 0.0366, "step": 261000 }, { "epoch": 1.43, "learning_rate": 1.0443823201593306e-05, "loss": 0.041, "step": 261500 }, { "epoch": 1.44, "learning_rate": 1.0425551353030388e-05, "loss": 0.0277, "step": 262000 }, { "epoch": 1.44, "learning_rate": 1.0407279504467467e-05, "loss": 0.0321, "step": 262500 }, { "epoch": 1.44, "learning_rate": 1.0389007655904548e-05, "loss": 0.0412, "step": 263000 }, { "epoch": 1.44, "learning_rate": 1.037073580734163e-05, "loss": 0.0411, "step": 263500 }, { "epoch": 1.45, "learning_rate": 1.035246395877871e-05, "loss": 0.0294, "step": 264000 }, { "epoch": 1.45, "learning_rate": 1.033419211021579e-05, "loss": 0.0361, "step": 264500 }, { "epoch": 1.45, "learning_rate": 1.0315920261652872e-05, "loss": 0.0506, "step": 265000 }, { "epoch": 1.46, "learning_rate": 1.0297648413089953e-05, "loss": 0.038, "step": 265500 }, { "epoch": 1.46, "learning_rate": 1.0279376564527035e-05, "loss": 0.0323, "step": 266000 }, { "epoch": 1.46, "learning_rate": 1.0261104715964114e-05, "loss": 0.0346, "step": 266500 }, { "epoch": 1.46, "learning_rate": 1.0242832867401195e-05, "loss": 0.0336, "step": 267000 }, { "epoch": 1.47, "learning_rate": 1.0224561018838277e-05, "loss": 0.0387, "step": 267500 }, { "epoch": 1.47, "learning_rate": 1.0206289170275358e-05, "loss": 0.0362, "step": 268000 }, { "epoch": 1.47, "learning_rate": 1.0188017321712437e-05, "loss": 0.0304, "step": 268500 }, { "epoch": 1.47, "learning_rate": 1.016974547314952e-05, "loss": 0.038, "step": 269000 }, { "epoch": 1.48, "learning_rate": 1.01514736245866e-05, "loss": 0.036, "step": 269500 }, { "epoch": 1.48, "learning_rate": 1.013320177602368e-05, "loss": 0.0385, "step": 270000 }, { "epoch": 1.48, "learning_rate": 1.0114929927460762e-05, "loss": 0.033, "step": 270500 }, { "epoch": 1.49, "learning_rate": 1.0096658078897842e-05, "loss": 0.0283, "step": 271000 }, { "epoch": 1.49, "learning_rate": 1.0078386230334925e-05, "loss": 0.0372, "step": 271500 }, { "epoch": 1.49, "learning_rate": 1.0060114381772004e-05, "loss": 0.0387, "step": 272000 }, { "epoch": 1.49, "learning_rate": 1.0041842533209086e-05, "loss": 0.0378, "step": 272500 }, { "epoch": 1.5, "learning_rate": 1.0023570684646167e-05, "loss": 0.0308, "step": 273000 }, { "epoch": 1.5, "learning_rate": 1.0005298836083247e-05, "loss": 0.0363, "step": 273500 }, { "epoch": 1.5, "learning_rate": 9.987026987520328e-06, "loss": 0.0289, "step": 274000 }, { "epoch": 1.5, "learning_rate": 9.968755138957409e-06, "loss": 0.0329, "step": 274500 }, { "epoch": 1.51, "learning_rate": 9.95048329039449e-06, "loss": 0.0385, "step": 275000 }, { "epoch": 1.51, "learning_rate": 9.93221144183157e-06, "loss": 0.0415, "step": 275500 }, { "epoch": 1.51, "learning_rate": 9.913939593268653e-06, "loss": 0.0353, "step": 276000 }, { "epoch": 1.52, "learning_rate": 9.895667744705733e-06, "loss": 0.0308, "step": 276500 }, { "epoch": 1.52, "learning_rate": 9.877395896142814e-06, "loss": 0.0356, "step": 277000 }, { "epoch": 1.52, "learning_rate": 9.859124047579895e-06, "loss": 0.0348, "step": 277500 }, { "epoch": 1.52, "learning_rate": 9.840852199016975e-06, "loss": 0.0439, "step": 278000 }, { "epoch": 1.53, "learning_rate": 9.822580350454056e-06, "loss": 0.0329, "step": 278500 }, { "epoch": 1.53, "learning_rate": 9.804308501891137e-06, "loss": 0.0386, "step": 279000 }, { "epoch": 1.53, "learning_rate": 9.786036653328217e-06, "loss": 0.0445, "step": 279500 }, { "epoch": 1.53, "learning_rate": 9.767764804765298e-06, "loss": 0.0385, "step": 280000 }, { "epoch": 1.54, "learning_rate": 9.74949295620238e-06, "loss": 0.0308, "step": 280500 }, { "epoch": 1.54, "learning_rate": 9.73122110763946e-06, "loss": 0.0322, "step": 281000 }, { "epoch": 1.54, "learning_rate": 9.712949259076542e-06, "loss": 0.0424, "step": 281500 }, { "epoch": 1.55, "learning_rate": 9.694677410513623e-06, "loss": 0.0274, "step": 282000 }, { "epoch": 1.55, "learning_rate": 9.676405561950703e-06, "loss": 0.0471, "step": 282500 }, { "epoch": 1.55, "learning_rate": 9.658133713387784e-06, "loss": 0.0425, "step": 283000 }, { "epoch": 1.55, "learning_rate": 9.639861864824865e-06, "loss": 0.0353, "step": 283500 }, { "epoch": 1.56, "learning_rate": 9.621590016261945e-06, "loss": 0.0364, "step": 284000 }, { "epoch": 1.56, "learning_rate": 9.603318167699028e-06, "loss": 0.0258, "step": 284500 }, { "epoch": 1.56, "learning_rate": 9.585046319136107e-06, "loss": 0.0458, "step": 285000 }, { "epoch": 1.56, "learning_rate": 9.56677447057319e-06, "loss": 0.0319, "step": 285500 }, { "epoch": 1.57, "learning_rate": 9.54850262201027e-06, "loss": 0.045, "step": 286000 }, { "epoch": 1.57, "learning_rate": 9.53023077344735e-06, "loss": 0.0317, "step": 286500 }, { "epoch": 1.57, "learning_rate": 9.511958924884431e-06, "loss": 0.0307, "step": 287000 }, { "epoch": 1.58, "learning_rate": 9.493687076321512e-06, "loss": 0.0373, "step": 287500 }, { "epoch": 1.58, "learning_rate": 9.475415227758593e-06, "loss": 0.0294, "step": 288000 }, { "epoch": 1.58, "learning_rate": 9.457143379195673e-06, "loss": 0.038, "step": 288500 }, { "epoch": 1.58, "learning_rate": 9.438871530632754e-06, "loss": 0.0328, "step": 289000 }, { "epoch": 1.59, "learning_rate": 9.420599682069835e-06, "loss": 0.0416, "step": 289500 }, { "epoch": 1.59, "learning_rate": 9.402327833506917e-06, "loss": 0.033, "step": 290000 }, { "epoch": 1.59, "learning_rate": 9.384055984943998e-06, "loss": 0.0253, "step": 290500 }, { "epoch": 1.6, "learning_rate": 9.365784136381079e-06, "loss": 0.0316, "step": 291000 }, { "epoch": 1.6, "learning_rate": 9.34751228781816e-06, "loss": 0.0327, "step": 291500 }, { "epoch": 1.6, "learning_rate": 9.32924043925524e-06, "loss": 0.0287, "step": 292000 }, { "epoch": 1.6, "learning_rate": 9.31096859069232e-06, "loss": 0.0327, "step": 292500 }, { "epoch": 1.61, "learning_rate": 9.292696742129403e-06, "loss": 0.0341, "step": 293000 }, { "epoch": 1.61, "learning_rate": 9.274424893566482e-06, "loss": 0.0399, "step": 293500 }, { "epoch": 1.61, "learning_rate": 9.256153045003565e-06, "loss": 0.021, "step": 294000 }, { "epoch": 1.61, "learning_rate": 9.237881196440645e-06, "loss": 0.0511, "step": 294500 }, { "epoch": 1.62, "learning_rate": 9.219609347877726e-06, "loss": 0.0241, "step": 295000 }, { "epoch": 1.62, "learning_rate": 9.201337499314807e-06, "loss": 0.0296, "step": 295500 }, { "epoch": 1.62, "learning_rate": 9.183065650751887e-06, "loss": 0.037, "step": 296000 }, { "epoch": 1.63, "learning_rate": 9.164793802188968e-06, "loss": 0.0362, "step": 296500 }, { "epoch": 1.63, "learning_rate": 9.146521953626049e-06, "loss": 0.0349, "step": 297000 }, { "epoch": 1.63, "learning_rate": 9.12825010506313e-06, "loss": 0.0367, "step": 297500 }, { "epoch": 1.63, "learning_rate": 9.10997825650021e-06, "loss": 0.0343, "step": 298000 }, { "epoch": 1.64, "learning_rate": 9.091706407937293e-06, "loss": 0.0296, "step": 298500 }, { "epoch": 1.64, "learning_rate": 9.073434559374372e-06, "loss": 0.0305, "step": 299000 }, { "epoch": 1.64, "learning_rate": 9.055162710811454e-06, "loss": 0.0389, "step": 299500 }, { "epoch": 1.64, "learning_rate": 9.036890862248535e-06, "loss": 0.0324, "step": 300000 }, { "epoch": 1.65, "learning_rate": 9.018619013685615e-06, "loss": 0.0243, "step": 300500 }, { "epoch": 1.65, "learning_rate": 9.000347165122696e-06, "loss": 0.0287, "step": 301000 }, { "epoch": 1.65, "learning_rate": 8.982075316559777e-06, "loss": 0.0306, "step": 301500 }, { "epoch": 1.66, "learning_rate": 8.963803467996857e-06, "loss": 0.0323, "step": 302000 }, { "epoch": 1.66, "learning_rate": 8.94553161943394e-06, "loss": 0.0309, "step": 302500 }, { "epoch": 1.66, "learning_rate": 8.927259770871019e-06, "loss": 0.031, "step": 303000 }, { "epoch": 1.66, "learning_rate": 8.908987922308101e-06, "loss": 0.0367, "step": 303500 }, { "epoch": 1.67, "learning_rate": 8.890716073745182e-06, "loss": 0.0331, "step": 304000 }, { "epoch": 1.67, "learning_rate": 8.872444225182263e-06, "loss": 0.0323, "step": 304500 }, { "epoch": 1.67, "learning_rate": 8.854172376619343e-06, "loss": 0.0362, "step": 305000 }, { "epoch": 1.67, "learning_rate": 8.835900528056424e-06, "loss": 0.0269, "step": 305500 }, { "epoch": 1.68, "learning_rate": 8.817628679493505e-06, "loss": 0.0395, "step": 306000 }, { "epoch": 1.68, "learning_rate": 8.799356830930585e-06, "loss": 0.0424, "step": 306500 }, { "epoch": 1.68, "learning_rate": 8.781084982367666e-06, "loss": 0.0296, "step": 307000 }, { "epoch": 1.69, "learning_rate": 8.762813133804747e-06, "loss": 0.0375, "step": 307500 }, { "epoch": 1.69, "learning_rate": 8.74454128524183e-06, "loss": 0.0321, "step": 308000 }, { "epoch": 1.69, "learning_rate": 8.72626943667891e-06, "loss": 0.0321, "step": 308500 }, { "epoch": 1.69, "learning_rate": 8.70799758811599e-06, "loss": 0.0331, "step": 309000 }, { "epoch": 1.7, "learning_rate": 8.689725739553071e-06, "loss": 0.0259, "step": 309500 }, { "epoch": 1.7, "learning_rate": 8.671453890990152e-06, "loss": 0.0258, "step": 310000 }, { "epoch": 1.7, "learning_rate": 8.653182042427233e-06, "loss": 0.035, "step": 310500 }, { "epoch": 1.7, "learning_rate": 8.634910193864315e-06, "loss": 0.027, "step": 311000 }, { "epoch": 1.71, "learning_rate": 8.616638345301394e-06, "loss": 0.0329, "step": 311500 }, { "epoch": 1.71, "learning_rate": 8.598366496738476e-06, "loss": 0.021, "step": 312000 }, { "epoch": 1.71, "learning_rate": 8.580094648175557e-06, "loss": 0.0329, "step": 312500 }, { "epoch": 1.72, "learning_rate": 8.561822799612638e-06, "loss": 0.0496, "step": 313000 }, { "epoch": 1.72, "learning_rate": 8.543550951049719e-06, "loss": 0.0434, "step": 313500 }, { "epoch": 1.72, "learning_rate": 8.5252791024868e-06, "loss": 0.0299, "step": 314000 }, { "epoch": 1.72, "learning_rate": 8.50700725392388e-06, "loss": 0.0358, "step": 314500 }, { "epoch": 1.73, "learning_rate": 8.48873540536096e-06, "loss": 0.0337, "step": 315000 }, { "epoch": 1.73, "learning_rate": 8.470463556798041e-06, "loss": 0.0348, "step": 315500 }, { "epoch": 1.73, "learning_rate": 8.452191708235122e-06, "loss": 0.0372, "step": 316000 }, { "epoch": 1.73, "learning_rate": 8.433919859672204e-06, "loss": 0.0284, "step": 316500 }, { "epoch": 1.74, "learning_rate": 8.415648011109283e-06, "loss": 0.0297, "step": 317000 }, { "epoch": 1.74, "learning_rate": 8.397376162546366e-06, "loss": 0.0294, "step": 317500 }, { "epoch": 1.74, "learning_rate": 8.379104313983447e-06, "loss": 0.0302, "step": 318000 }, { "epoch": 1.75, "learning_rate": 8.360832465420527e-06, "loss": 0.0305, "step": 318500 }, { "epoch": 1.75, "learning_rate": 8.342560616857608e-06, "loss": 0.0222, "step": 319000 }, { "epoch": 1.75, "learning_rate": 8.324288768294689e-06, "loss": 0.0289, "step": 319500 }, { "epoch": 1.75, "learning_rate": 8.30601691973177e-06, "loss": 0.0253, "step": 320000 }, { "epoch": 1.76, "learning_rate": 8.287745071168852e-06, "loss": 0.0365, "step": 320500 }, { "epoch": 1.76, "learning_rate": 8.26947322260593e-06, "loss": 0.0357, "step": 321000 }, { "epoch": 1.76, "learning_rate": 8.251201374043013e-06, "loss": 0.0365, "step": 321500 }, { "epoch": 1.77, "learning_rate": 8.232929525480094e-06, "loss": 0.0324, "step": 322000 }, { "epoch": 1.77, "learning_rate": 8.214657676917175e-06, "loss": 0.0319, "step": 322500 }, { "epoch": 1.77, "learning_rate": 8.196385828354255e-06, "loss": 0.0339, "step": 323000 }, { "epoch": 1.77, "learning_rate": 8.178113979791336e-06, "loss": 0.0271, "step": 323500 }, { "epoch": 1.78, "learning_rate": 8.159842131228417e-06, "loss": 0.031, "step": 324000 }, { "epoch": 1.78, "learning_rate": 8.141570282665497e-06, "loss": 0.0304, "step": 324500 }, { "epoch": 1.78, "learning_rate": 8.123298434102578e-06, "loss": 0.0335, "step": 325000 }, { "epoch": 1.78, "learning_rate": 8.105026585539659e-06, "loss": 0.0321, "step": 325500 }, { "epoch": 1.79, "learning_rate": 8.086754736976741e-06, "loss": 0.0231, "step": 326000 }, { "epoch": 1.79, "learning_rate": 8.068482888413822e-06, "loss": 0.0433, "step": 326500 }, { "epoch": 1.79, "learning_rate": 8.050211039850903e-06, "loss": 0.0387, "step": 327000 }, { "epoch": 1.8, "learning_rate": 8.031939191287983e-06, "loss": 0.038, "step": 327500 }, { "epoch": 1.8, "learning_rate": 8.013667342725064e-06, "loss": 0.0336, "step": 328000 }, { "epoch": 1.8, "learning_rate": 7.995395494162145e-06, "loss": 0.0404, "step": 328500 }, { "epoch": 1.8, "learning_rate": 7.977123645599227e-06, "loss": 0.025, "step": 329000 }, { "epoch": 1.81, "learning_rate": 7.958851797036306e-06, "loss": 0.0259, "step": 329500 }, { "epoch": 1.81, "learning_rate": 7.940579948473388e-06, "loss": 0.0327, "step": 330000 }, { "epoch": 1.81, "learning_rate": 7.922308099910469e-06, "loss": 0.0227, "step": 330500 }, { "epoch": 1.81, "learning_rate": 7.90403625134755e-06, "loss": 0.0393, "step": 331000 }, { "epoch": 1.82, "learning_rate": 7.88576440278463e-06, "loss": 0.0336, "step": 331500 }, { "epoch": 1.82, "learning_rate": 7.867492554221711e-06, "loss": 0.026, "step": 332000 }, { "epoch": 1.82, "learning_rate": 7.849220705658792e-06, "loss": 0.0341, "step": 332500 }, { "epoch": 1.83, "learning_rate": 7.830948857095873e-06, "loss": 0.0322, "step": 333000 }, { "epoch": 1.83, "learning_rate": 7.812677008532953e-06, "loss": 0.0307, "step": 333500 }, { "epoch": 1.83, "learning_rate": 7.794405159970034e-06, "loss": 0.0321, "step": 334000 }, { "epoch": 1.83, "learning_rate": 7.776133311407116e-06, "loss": 0.0319, "step": 334500 }, { "epoch": 1.84, "learning_rate": 7.757861462844195e-06, "loss": 0.0265, "step": 335000 }, { "epoch": 1.84, "learning_rate": 7.739589614281278e-06, "loss": 0.0357, "step": 335500 }, { "epoch": 1.84, "learning_rate": 7.721317765718359e-06, "loss": 0.0284, "step": 336000 }, { "epoch": 1.84, "learning_rate": 7.70304591715544e-06, "loss": 0.0337, "step": 336500 }, { "epoch": 1.85, "learning_rate": 7.68477406859252e-06, "loss": 0.0263, "step": 337000 }, { "epoch": 1.85, "learning_rate": 7.6665022200296e-06, "loss": 0.0292, "step": 337500 }, { "epoch": 1.85, "learning_rate": 7.648230371466681e-06, "loss": 0.0239, "step": 338000 }, { "epoch": 1.86, "learning_rate": 7.629958522903764e-06, "loss": 0.0426, "step": 338500 }, { "epoch": 1.86, "learning_rate": 7.6116866743408436e-06, "loss": 0.0303, "step": 339000 }, { "epoch": 1.86, "learning_rate": 7.593414825777925e-06, "loss": 0.0347, "step": 339500 }, { "epoch": 1.86, "learning_rate": 7.575142977215005e-06, "loss": 0.037, "step": 340000 }, { "epoch": 1.87, "learning_rate": 7.5568711286520865e-06, "loss": 0.0295, "step": 340500 }, { "epoch": 1.87, "learning_rate": 7.538599280089167e-06, "loss": 0.0261, "step": 341000 }, { "epoch": 1.87, "learning_rate": 7.520327431526249e-06, "loss": 0.0329, "step": 341500 }, { "epoch": 1.87, "learning_rate": 7.502055582963329e-06, "loss": 0.0392, "step": 342000 }, { "epoch": 1.88, "learning_rate": 7.483783734400409e-06, "loss": 0.0299, "step": 342500 }, { "epoch": 1.88, "learning_rate": 7.465511885837491e-06, "loss": 0.0313, "step": 343000 }, { "epoch": 1.88, "learning_rate": 7.4472400372745716e-06, "loss": 0.0312, "step": 343500 }, { "epoch": 1.89, "learning_rate": 7.428968188711653e-06, "loss": 0.0329, "step": 344000 }, { "epoch": 1.89, "learning_rate": 7.410696340148733e-06, "loss": 0.0227, "step": 344500 }, { "epoch": 1.89, "learning_rate": 7.3924244915858145e-06, "loss": 0.0264, "step": 345000 }, { "epoch": 1.89, "learning_rate": 7.374152643022895e-06, "loss": 0.0277, "step": 345500 }, { "epoch": 1.9, "learning_rate": 7.355880794459977e-06, "loss": 0.0301, "step": 346000 }, { "epoch": 1.9, "learning_rate": 7.337608945897057e-06, "loss": 0.035, "step": 346500 }, { "epoch": 1.9, "learning_rate": 7.319337097334138e-06, "loss": 0.0374, "step": 347000 }, { "epoch": 1.9, "learning_rate": 7.301065248771219e-06, "loss": 0.0193, "step": 347500 }, { "epoch": 1.91, "learning_rate": 7.2827934002083e-06, "loss": 0.0264, "step": 348000 }, { "epoch": 1.91, "learning_rate": 7.26452155164538e-06, "loss": 0.034, "step": 348500 }, { "epoch": 1.91, "learning_rate": 7.246249703082462e-06, "loss": 0.0288, "step": 349000 }, { "epoch": 1.92, "learning_rate": 7.2279778545195425e-06, "loss": 0.0323, "step": 349500 }, { "epoch": 1.92, "learning_rate": 7.209706005956624e-06, "loss": 0.0279, "step": 350000 }, { "epoch": 1.92, "learning_rate": 7.191434157393704e-06, "loss": 0.0285, "step": 350500 }, { "epoch": 1.92, "learning_rate": 7.173162308830785e-06, "loss": 0.0383, "step": 351000 }, { "epoch": 1.93, "learning_rate": 7.154890460267866e-06, "loss": 0.033, "step": 351500 }, { "epoch": 1.93, "learning_rate": 7.136618611704946e-06, "loss": 0.0347, "step": 352000 }, { "epoch": 1.93, "learning_rate": 7.1183467631420275e-06, "loss": 0.0314, "step": 352500 }, { "epoch": 1.93, "learning_rate": 7.100074914579108e-06, "loss": 0.0306, "step": 353000 }, { "epoch": 1.94, "learning_rate": 7.08180306601619e-06, "loss": 0.0464, "step": 353500 }, { "epoch": 1.94, "learning_rate": 7.06353121745327e-06, "loss": 0.0314, "step": 354000 }, { "epoch": 1.94, "learning_rate": 7.045259368890351e-06, "loss": 0.0206, "step": 354500 }, { "epoch": 1.95, "learning_rate": 7.026987520327432e-06, "loss": 0.0206, "step": 355000 }, { "epoch": 1.95, "learning_rate": 7.008715671764513e-06, "loss": 0.0222, "step": 355500 }, { "epoch": 1.95, "learning_rate": 6.990443823201593e-06, "loss": 0.0324, "step": 356000 }, { "epoch": 1.95, "learning_rate": 6.972171974638675e-06, "loss": 0.0431, "step": 356500 }, { "epoch": 1.96, "learning_rate": 6.9539001260757555e-06, "loss": 0.0363, "step": 357000 }, { "epoch": 1.96, "learning_rate": 6.935628277512837e-06, "loss": 0.0307, "step": 357500 }, { "epoch": 1.96, "learning_rate": 6.917356428949917e-06, "loss": 0.0223, "step": 358000 }, { "epoch": 1.97, "learning_rate": 6.8990845803869985e-06, "loss": 0.0276, "step": 358500 }, { "epoch": 1.97, "learning_rate": 6.880812731824079e-06, "loss": 0.0283, "step": 359000 }, { "epoch": 1.97, "learning_rate": 6.862540883261161e-06, "loss": 0.0323, "step": 359500 }, { "epoch": 1.97, "learning_rate": 6.844269034698241e-06, "loss": 0.0323, "step": 360000 }, { "epoch": 1.98, "learning_rate": 6.825997186135321e-06, "loss": 0.0334, "step": 360500 }, { "epoch": 1.98, "learning_rate": 6.807725337572403e-06, "loss": 0.0325, "step": 361000 }, { "epoch": 1.98, "learning_rate": 6.7894534890094835e-06, "loss": 0.0333, "step": 361500 }, { "epoch": 1.98, "learning_rate": 6.771181640446565e-06, "loss": 0.0287, "step": 362000 }, { "epoch": 1.99, "learning_rate": 6.752909791883645e-06, "loss": 0.0192, "step": 362500 }, { "epoch": 1.99, "learning_rate": 6.7346379433207264e-06, "loss": 0.03, "step": 363000 }, { "epoch": 1.99, "learning_rate": 6.716366094757807e-06, "loss": 0.0238, "step": 363500 }, { "epoch": 2.0, "learning_rate": 6.698094246194889e-06, "loss": 0.0262, "step": 364000 }, { "epoch": 2.0, "learning_rate": 6.6798223976319685e-06, "loss": 0.0262, "step": 364500 }, { "epoch": 2.0, "eval_loss": 0.14961867034435272, "eval_runtime": 1674.7145, "eval_samples_per_second": 138.344, "eval_steps_per_second": 13.835, "step": 364860 } ], "max_steps": 547290, "num_train_epochs": 3, "total_flos": 7.150255099702272e+17, "trial_name": null, "trial_params": null }