{ "best_metric": null, "best_model_checkpoint": null, "epoch": 10.0, "global_step": 79270, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.03, "learning_rate": 4.9474370295614146e-05, "loss": 6.7026, "step": 500 }, { "epoch": 0.06, "learning_rate": 4.894874059122829e-05, "loss": 5.9908, "step": 1000 }, { "epoch": 0.09, "learning_rate": 4.842311088684244e-05, "loss": 5.8689, "step": 1500 }, { "epoch": 0.13, "learning_rate": 4.7897481182456584e-05, "loss": 5.8051, "step": 2000 }, { "epoch": 0.16, "learning_rate": 4.7371851478070734e-05, "loss": 5.7614, "step": 2500 }, { "epoch": 0.19, "learning_rate": 4.684622177368488e-05, "loss": 5.7379, "step": 3000 }, { "epoch": 0.22, "learning_rate": 4.632059206929902e-05, "loss": 5.732, "step": 3500 }, { "epoch": 0.25, "learning_rate": 4.579496236491317e-05, "loss": 5.6936, "step": 4000 }, { "epoch": 0.28, "learning_rate": 4.5269332660527315e-05, "loss": 5.6739, "step": 4500 }, { "epoch": 0.32, "learning_rate": 4.474370295614146e-05, "loss": 5.6779, "step": 5000 }, { "epoch": 0.35, "learning_rate": 4.42180732517556e-05, "loss": 5.6697, "step": 5500 }, { "epoch": 0.38, "learning_rate": 4.3692443547369746e-05, "loss": 5.6401, "step": 6000 }, { "epoch": 0.41, "learning_rate": 4.3166813842983896e-05, "loss": 5.645, "step": 6500 }, { "epoch": 0.44, "learning_rate": 4.264118413859805e-05, "loss": 5.6403, "step": 7000 }, { "epoch": 0.47, "learning_rate": 4.211555443421219e-05, "loss": 5.612, "step": 7500 }, { "epoch": 0.5, "learning_rate": 4.1589924729826334e-05, "loss": 5.5909, "step": 8000 }, { "epoch": 0.54, "learning_rate": 4.106429502544048e-05, "loss": 5.6036, "step": 8500 }, { "epoch": 0.57, "learning_rate": 4.053866532105463e-05, "loss": 5.5978, "step": 9000 }, { "epoch": 0.6, "learning_rate": 4.001303561666877e-05, "loss": 5.5889, "step": 9500 }, { "epoch": 0.63, "learning_rate": 3.9487405912282915e-05, "loss": 5.5751, "step": 10000 }, { "epoch": 0.66, "learning_rate": 3.896177620789706e-05, "loss": 5.5676, "step": 10500 }, { "epoch": 0.69, "learning_rate": 3.84361465035112e-05, "loss": 5.5704, "step": 11000 }, { "epoch": 0.73, "learning_rate": 3.791051679912536e-05, "loss": 5.5815, "step": 11500 }, { "epoch": 0.76, "learning_rate": 3.73848870947395e-05, "loss": 5.5608, "step": 12000 }, { "epoch": 0.79, "learning_rate": 3.685925739035365e-05, "loss": 5.5582, "step": 12500 }, { "epoch": 0.82, "learning_rate": 3.633362768596779e-05, "loss": 5.5498, "step": 13000 }, { "epoch": 0.85, "learning_rate": 3.5807997981581934e-05, "loss": 5.5301, "step": 13500 }, { "epoch": 0.88, "learning_rate": 3.5282368277196084e-05, "loss": 5.554, "step": 14000 }, { "epoch": 0.91, "learning_rate": 3.475673857281023e-05, "loss": 5.5397, "step": 14500 }, { "epoch": 0.95, "learning_rate": 3.423110886842437e-05, "loss": 5.5245, "step": 15000 }, { "epoch": 0.98, "learning_rate": 3.3705479164038515e-05, "loss": 5.525, "step": 15500 }, { "epoch": 1.01, "learning_rate": 3.3179849459652665e-05, "loss": 5.5016, "step": 16000 }, { "epoch": 1.04, "learning_rate": 3.2654219755266816e-05, "loss": 5.5208, "step": 16500 }, { "epoch": 1.07, "learning_rate": 3.212859005088096e-05, "loss": 5.5018, "step": 17000 }, { "epoch": 1.1, "learning_rate": 3.16029603464951e-05, "loss": 5.5157, "step": 17500 }, { "epoch": 1.14, "learning_rate": 3.107733064210925e-05, "loss": 5.4933, "step": 18000 }, { "epoch": 1.17, "learning_rate": 3.055170093772339e-05, "loss": 5.4974, "step": 18500 }, { "epoch": 1.2, "learning_rate": 3.0026071233337537e-05, "loss": 5.4927, "step": 19000 }, { "epoch": 1.23, "learning_rate": 2.9500441528951684e-05, "loss": 5.4934, "step": 19500 }, { "epoch": 1.26, "learning_rate": 2.8974811824565835e-05, "loss": 5.4849, "step": 20000 }, { "epoch": 1.29, "learning_rate": 2.8449182120179978e-05, "loss": 5.4777, "step": 20500 }, { "epoch": 1.32, "learning_rate": 2.7923552415794125e-05, "loss": 5.4695, "step": 21000 }, { "epoch": 1.36, "learning_rate": 2.739792271140827e-05, "loss": 5.4752, "step": 21500 }, { "epoch": 1.39, "learning_rate": 2.6872293007022416e-05, "loss": 5.4666, "step": 22000 }, { "epoch": 1.42, "learning_rate": 2.634666330263656e-05, "loss": 5.4621, "step": 22500 }, { "epoch": 1.45, "learning_rate": 2.5821033598250703e-05, "loss": 5.4808, "step": 23000 }, { "epoch": 1.48, "learning_rate": 2.529540389386485e-05, "loss": 5.4628, "step": 23500 }, { "epoch": 1.51, "learning_rate": 2.4769774189478997e-05, "loss": 5.4594, "step": 24000 }, { "epoch": 1.55, "learning_rate": 2.4244144485093144e-05, "loss": 5.4557, "step": 24500 }, { "epoch": 1.58, "learning_rate": 2.3718514780707288e-05, "loss": 5.4599, "step": 25000 }, { "epoch": 1.61, "learning_rate": 2.319288507632143e-05, "loss": 5.4493, "step": 25500 }, { "epoch": 1.64, "learning_rate": 2.266725537193558e-05, "loss": 5.4542, "step": 26000 }, { "epoch": 1.67, "learning_rate": 2.2141625667549725e-05, "loss": 5.4319, "step": 26500 }, { "epoch": 1.7, "learning_rate": 2.1615995963163872e-05, "loss": 5.4439, "step": 27000 }, { "epoch": 1.73, "learning_rate": 2.1090366258778016e-05, "loss": 5.4309, "step": 27500 }, { "epoch": 1.77, "learning_rate": 2.0564736554392163e-05, "loss": 5.4249, "step": 28000 }, { "epoch": 1.8, "learning_rate": 2.003910685000631e-05, "loss": 5.4351, "step": 28500 }, { "epoch": 1.83, "learning_rate": 1.9513477145620453e-05, "loss": 5.427, "step": 29000 }, { "epoch": 1.86, "learning_rate": 1.89878474412346e-05, "loss": 5.4111, "step": 29500 }, { "epoch": 1.89, "learning_rate": 1.8462217736848747e-05, "loss": 5.4172, "step": 30000 }, { "epoch": 1.92, "learning_rate": 1.793658803246289e-05, "loss": 5.4098, "step": 30500 }, { "epoch": 1.96, "learning_rate": 1.7410958328077038e-05, "loss": 5.3989, "step": 31000 }, { "epoch": 1.99, "learning_rate": 1.688532862369118e-05, "loss": 5.4145, "step": 31500 }, { "epoch": 2.02, "learning_rate": 1.635969891930533e-05, "loss": 5.4077, "step": 32000 }, { "epoch": 2.05, "learning_rate": 1.5834069214919476e-05, "loss": 5.4025, "step": 32500 }, { "epoch": 2.08, "learning_rate": 1.530843951053362e-05, "loss": 5.4119, "step": 33000 }, { "epoch": 2.11, "learning_rate": 1.4782809806147766e-05, "loss": 5.3939, "step": 33500 }, { "epoch": 2.14, "learning_rate": 1.425718010176191e-05, "loss": 5.4162, "step": 34000 }, { "epoch": 2.18, "learning_rate": 1.3731550397376058e-05, "loss": 5.4015, "step": 34500 }, { "epoch": 2.21, "learning_rate": 1.3205920692990204e-05, "loss": 5.4026, "step": 35000 }, { "epoch": 2.24, "learning_rate": 1.2680290988604349e-05, "loss": 5.3821, "step": 35500 }, { "epoch": 2.27, "learning_rate": 1.2154661284218494e-05, "loss": 5.3729, "step": 36000 }, { "epoch": 2.3, "learning_rate": 1.162903157983264e-05, "loss": 5.3854, "step": 36500 }, { "epoch": 2.33, "learning_rate": 1.1103401875446785e-05, "loss": 5.3743, "step": 37000 }, { "epoch": 2.37, "learning_rate": 1.0577772171060932e-05, "loss": 5.3816, "step": 37500 }, { "epoch": 2.4, "learning_rate": 1.0052142466675077e-05, "loss": 5.3738, "step": 38000 }, { "epoch": 2.43, "learning_rate": 9.526512762289224e-06, "loss": 5.3845, "step": 38500 }, { "epoch": 2.46, "learning_rate": 9.000883057903368e-06, "loss": 5.3781, "step": 39000 }, { "epoch": 2.49, "learning_rate": 8.475253353517515e-06, "loss": 5.3802, "step": 39500 }, { "epoch": 2.52, "learning_rate": 7.94962364913166e-06, "loss": 5.3651, "step": 40000 }, { "epoch": 2.55, "learning_rate": 7.423993944745806e-06, "loss": 5.3736, "step": 40500 }, { "epoch": 2.59, "learning_rate": 6.8983642403599515e-06, "loss": 5.3689, "step": 41000 }, { "epoch": 2.62, "learning_rate": 6.372734535974097e-06, "loss": 5.3817, "step": 41500 }, { "epoch": 2.65, "learning_rate": 5.847104831588243e-06, "loss": 5.3764, "step": 42000 }, { "epoch": 2.68, "learning_rate": 5.321475127202389e-06, "loss": 5.3618, "step": 42500 }, { "epoch": 2.71, "learning_rate": 4.795845422816534e-06, "loss": 5.361, "step": 43000 }, { "epoch": 2.74, "learning_rate": 4.27021571843068e-06, "loss": 5.3575, "step": 43500 }, { "epoch": 2.78, "learning_rate": 3.744586014044826e-06, "loss": 5.3689, "step": 44000 }, { "epoch": 2.81, "learning_rate": 3.2189563096589715e-06, "loss": 5.3684, "step": 44500 }, { "epoch": 2.84, "learning_rate": 2.6933266052731173e-06, "loss": 5.3442, "step": 45000 }, { "epoch": 2.87, "learning_rate": 2.167696900887263e-06, "loss": 5.3602, "step": 45500 }, { "epoch": 2.9, "learning_rate": 1.6420671965014087e-06, "loss": 5.3636, "step": 46000 }, { "epoch": 2.93, "learning_rate": 1.1164374921155544e-06, "loss": 5.3474, "step": 46500 }, { "epoch": 2.96, "learning_rate": 5.908077877297002e-07, "loss": 5.3501, "step": 47000 }, { "epoch": 3.0, "learning_rate": 6.517808334384593e-08, "loss": 5.3521, "step": 47500 }, { "epoch": 6.06, "learning_rate": 1.9723729027374795e-05, "loss": 5.3624, "step": 48000 }, { "epoch": 6.12, "learning_rate": 1.9408351204743284e-05, "loss": 5.3565, "step": 48500 }, { "epoch": 6.18, "learning_rate": 1.909297338211177e-05, "loss": 5.3609, "step": 49000 }, { "epoch": 6.24, "learning_rate": 1.877759555948026e-05, "loss": 5.3611, "step": 49500 }, { "epoch": 6.31, "learning_rate": 1.8462217736848747e-05, "loss": 5.3563, "step": 50000 }, { "epoch": 6.37, "learning_rate": 1.8146839914217233e-05, "loss": 5.3578, "step": 50500 }, { "epoch": 6.43, "learning_rate": 1.783146209158572e-05, "loss": 5.3396, "step": 51000 }, { "epoch": 6.5, "learning_rate": 1.7516084268954207e-05, "loss": 5.3496, "step": 51500 }, { "epoch": 6.56, "learning_rate": 1.7200706446322696e-05, "loss": 5.3486, "step": 52000 }, { "epoch": 6.62, "learning_rate": 1.688532862369118e-05, "loss": 5.3449, "step": 52500 }, { "epoch": 6.69, "learning_rate": 1.656995080105967e-05, "loss": 5.336, "step": 53000 }, { "epoch": 6.75, "learning_rate": 1.6254572978428156e-05, "loss": 5.3289, "step": 53500 }, { "epoch": 6.81, "learning_rate": 1.5939195155796645e-05, "loss": 5.3335, "step": 54000 }, { "epoch": 6.88, "learning_rate": 1.5623817333165134e-05, "loss": 5.3298, "step": 54500 }, { "epoch": 6.94, "learning_rate": 1.530843951053362e-05, "loss": 5.3302, "step": 55000 }, { "epoch": 7.0, "learning_rate": 1.4993061687902108e-05, "loss": 5.3275, "step": 55500 }, { "epoch": 7.06, "learning_rate": 1.4677683865270595e-05, "loss": 5.3219, "step": 56000 }, { "epoch": 7.13, "learning_rate": 1.4362306042639082e-05, "loss": 5.3179, "step": 56500 }, { "epoch": 7.19, "learning_rate": 1.4046928220007568e-05, "loss": 5.3064, "step": 57000 }, { "epoch": 7.25, "learning_rate": 1.3731550397376058e-05, "loss": 5.312, "step": 57500 }, { "epoch": 7.32, "learning_rate": 1.3416172574744546e-05, "loss": 5.3166, "step": 58000 }, { "epoch": 7.38, "learning_rate": 1.3100794752113033e-05, "loss": 5.308, "step": 58500 }, { "epoch": 7.44, "learning_rate": 1.278541692948152e-05, "loss": 5.2994, "step": 59000 }, { "epoch": 7.51, "learning_rate": 1.2470039106850007e-05, "loss": 5.2991, "step": 59500 }, { "epoch": 7.57, "learning_rate": 1.2154661284218494e-05, "loss": 5.2917, "step": 60000 }, { "epoch": 7.63, "learning_rate": 1.1839283461586981e-05, "loss": 5.2962, "step": 60500 }, { "epoch": 7.7, "learning_rate": 1.1523905638955469e-05, "loss": 5.2927, "step": 61000 }, { "epoch": 7.76, "learning_rate": 1.1208527816323956e-05, "loss": 5.2901, "step": 61500 }, { "epoch": 7.82, "learning_rate": 1.0893149993692445e-05, "loss": 5.2726, "step": 62000 }, { "epoch": 7.88, "learning_rate": 1.0577772171060932e-05, "loss": 5.2586, "step": 62500 }, { "epoch": 7.95, "learning_rate": 1.0262394348429419e-05, "loss": 5.2408, "step": 63000 }, { "epoch": 8.01, "learning_rate": 9.947016525797906e-06, "loss": 5.2086, "step": 63500 }, { "epoch": 8.07, "learning_rate": 9.631638703166395e-06, "loss": 5.1942, "step": 64000 }, { "epoch": 8.14, "learning_rate": 9.31626088053488e-06, "loss": 5.1737, "step": 64500 }, { "epoch": 8.2, "learning_rate": 9.000883057903368e-06, "loss": 5.1362, "step": 65000 }, { "epoch": 8.26, "learning_rate": 8.685505235271855e-06, "loss": 5.1235, "step": 65500 }, { "epoch": 8.33, "learning_rate": 8.370127412640344e-06, "loss": 5.0998, "step": 66000 }, { "epoch": 8.39, "learning_rate": 8.054749590008831e-06, "loss": 5.0742, "step": 66500 }, { "epoch": 8.45, "learning_rate": 7.739371767377318e-06, "loss": 5.0369, "step": 67000 }, { "epoch": 8.52, "learning_rate": 7.423993944745806e-06, "loss": 5.0226, "step": 67500 }, { "epoch": 8.58, "learning_rate": 7.108616122114293e-06, "loss": 4.9907, "step": 68000 }, { "epoch": 8.64, "learning_rate": 6.7932382994827806e-06, "loss": 4.9742, "step": 68500 }, { "epoch": 8.7, "learning_rate": 6.477860476851268e-06, "loss": 4.9379, "step": 69000 }, { "epoch": 8.77, "learning_rate": 6.162482654219756e-06, "loss": 4.9064, "step": 69500 }, { "epoch": 8.83, "learning_rate": 5.847104831588243e-06, "loss": 4.8912, "step": 70000 }, { "epoch": 8.89, "learning_rate": 5.53172700895673e-06, "loss": 4.8666, "step": 70500 }, { "epoch": 8.96, "learning_rate": 5.216349186325218e-06, "loss": 4.835, "step": 71000 }, { "epoch": 9.02, "learning_rate": 4.900971363693705e-06, "loss": 4.8144, "step": 71500 }, { "epoch": 9.08, "learning_rate": 4.5855935410621925e-06, "loss": 4.7944, "step": 72000 }, { "epoch": 9.15, "learning_rate": 4.27021571843068e-06, "loss": 4.7744, "step": 72500 }, { "epoch": 9.21, "learning_rate": 3.954837895799168e-06, "loss": 4.7491, "step": 73000 }, { "epoch": 9.27, "learning_rate": 3.6394600731676553e-06, "loss": 4.723, "step": 73500 }, { "epoch": 9.34, "learning_rate": 3.3240822505361425e-06, "loss": 4.7129, "step": 74000 }, { "epoch": 9.4, "learning_rate": 3.0087044279046297e-06, "loss": 4.6943, "step": 74500 }, { "epoch": 9.46, "learning_rate": 2.6933266052731173e-06, "loss": 4.6951, "step": 75000 }, { "epoch": 9.52, "learning_rate": 2.3779487826416044e-06, "loss": 4.6809, "step": 75500 }, { "epoch": 9.59, "learning_rate": 2.062570960010092e-06, "loss": 4.6689, "step": 76000 }, { "epoch": 9.65, "learning_rate": 1.7471931373785799e-06, "loss": 4.6579, "step": 76500 }, { "epoch": 9.71, "learning_rate": 1.431815314747067e-06, "loss": 4.6334, "step": 77000 }, { "epoch": 9.78, "learning_rate": 1.1164374921155544e-06, "loss": 4.6372, "step": 77500 }, { "epoch": 9.84, "learning_rate": 8.01059669484042e-07, "loss": 4.6378, "step": 78000 }, { "epoch": 9.9, "learning_rate": 4.856818468525293e-07, "loss": 4.6323, "step": 78500 }, { "epoch": 9.97, "learning_rate": 1.7030402422101678e-07, "loss": 4.6307, "step": 79000 }, { "epoch": 10.0, "step": 79270, "total_flos": 4.675970241591091e+17, "train_loss": 2.0376459330797827, "train_runtime": 6961.2818, "train_samples_per_second": 364.373, "train_steps_per_second": 11.387 } ], "max_steps": 79270, "num_train_epochs": 10, "total_flos": 4.675970241591091e+17, "trial_name": null, "trial_params": null }