| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.031905961376994, | |
| "global_step": 60500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0002992803166606693, | |
| "loss": 0.0141, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0002985606333213386, | |
| "loss": 0.0149, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0002978409499820079, | |
| "loss": 0.0134, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0002971212666426772, | |
| "loss": 0.0142, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0002964015833033465, | |
| "loss": 0.0147, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0002956818999640158, | |
| "loss": 0.0132, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0002949622166246851, | |
| "loss": 0.0137, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0002942425332853544, | |
| "loss": 0.0146, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0002935228499460237, | |
| "loss": 0.0146, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.000292803166606693, | |
| "loss": 0.0118, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00029208348326736233, | |
| "loss": 0.0144, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00029136379992803163, | |
| "loss": 0.0132, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00029064411658870094, | |
| "loss": 0.0122, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00028992443324937024, | |
| "loss": 0.011, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00028920474991003955, | |
| "loss": 0.0146, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00028848506657070885, | |
| "loss": 0.0128, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00028776538323137816, | |
| "loss": 0.0137, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00028704569989204746, | |
| "loss": 0.0133, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00028632601655271677, | |
| "loss": 0.0125, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00028560633321338607, | |
| "loss": 0.0134, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0002848866498740554, | |
| "loss": 0.0142, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0002841669665347247, | |
| "loss": 0.0126, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00028344728319539404, | |
| "loss": 0.0128, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0002827275998560633, | |
| "loss": 0.0126, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0002820079165167326, | |
| "loss": 0.0151, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0002812882331774019, | |
| "loss": 0.0127, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0002805685498380712, | |
| "loss": 0.0113, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00027984886649874057, | |
| "loss": 0.012, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0002791291831594098, | |
| "loss": 0.0137, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0002784094998200791, | |
| "loss": 0.0123, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.0002776898164807484, | |
| "loss": 0.013, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00027697013314141773, | |
| "loss": 0.0128, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.0002762504498020871, | |
| "loss": 0.0126, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0002755307664627564, | |
| "loss": 0.0141, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00027481108312342565, | |
| "loss": 0.0131, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00027409139978409495, | |
| "loss": 0.0138, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00027337171644476426, | |
| "loss": 0.0133, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0002726520331054336, | |
| "loss": 0.0123, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0002719323497661029, | |
| "loss": 0.0108, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00027121266642677217, | |
| "loss": 0.0131, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.0002704929830874415, | |
| "loss": 0.0111, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.0002697732997481108, | |
| "loss": 0.0128, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.00026905361640878014, | |
| "loss": 0.0118, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.00026833393306944944, | |
| "loss": 0.0125, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.00026761424973011875, | |
| "loss": 0.0123, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.000266894566390788, | |
| "loss": 0.0112, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.0002661748830514573, | |
| "loss": 0.0114, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.00026545519971212666, | |
| "loss": 0.0123, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.00026473551637279597, | |
| "loss": 0.012, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.0002640158330334653, | |
| "loss": 0.0113, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.0002632961496941345, | |
| "loss": 0.0124, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.00026257646635480383, | |
| "loss": 0.0128, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.0002618567830154732, | |
| "loss": 0.0122, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.0002611370996761425, | |
| "loss": 0.0118, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.0002604174163368118, | |
| "loss": 0.0138, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.0002596977329974811, | |
| "loss": 0.013, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.00025897804965815035, | |
| "loss": 0.0137, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.0002582583663188197, | |
| "loss": 0.012, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.000257538682979489, | |
| "loss": 0.0115, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_bleu": 41.1255, | |
| "eval_gen_len": 12.9555, | |
| "eval_loss": 0.009961633943021297, | |
| "eval_runtime": 1035.9589, | |
| "eval_samples_per_second": 12.775, | |
| "eval_steps_per_second": 6.387, | |
| "step": 29775 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.0002568189996401583, | |
| "loss": 0.0112, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.00025609931630082763, | |
| "loss": 0.0075, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.00025537963296149693, | |
| "loss": 0.0088, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.00025465994962216624, | |
| "loss": 0.0089, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.00025394026628283554, | |
| "loss": 0.0088, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.00025322058294350485, | |
| "loss": 0.0096, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.00025250089960417415, | |
| "loss": 0.009, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.00025178121626484346, | |
| "loss": 0.0097, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.00025106153292551276, | |
| "loss": 0.0086, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.00025034184958618207, | |
| "loss": 0.0093, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.00024962216624685137, | |
| "loss": 0.0097, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.0002489024829075207, | |
| "loss": 0.0095, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.00024818279956819, | |
| "loss": 0.0086, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.0002474631162288593, | |
| "loss": 0.0089, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.0002467434328895286, | |
| "loss": 0.0101, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.0002460237495501979, | |
| "loss": 0.009, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.0002453040662108672, | |
| "loss": 0.0084, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.0002445843828715365, | |
| "loss": 0.0099, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.0002438646995322058, | |
| "loss": 0.0088, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.00024314501619287512, | |
| "loss": 0.0096, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.00024242533285354442, | |
| "loss": 0.01, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.00024170564951421373, | |
| "loss": 0.0088, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.000240985966174883, | |
| "loss": 0.0101, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 0.00024026628283555234, | |
| "loss": 0.0093, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.00023954659949622164, | |
| "loss": 0.009, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 0.00023882691615689094, | |
| "loss": 0.0093, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.00023810723281756025, | |
| "loss": 0.0092, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 0.00023738754947822955, | |
| "loss": 0.01, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 0.0002366678661388989, | |
| "loss": 0.0089, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 0.00023594818279956816, | |
| "loss": 0.0079, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 0.00023522849946023747, | |
| "loss": 0.0091, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 0.00023450881612090677, | |
| "loss": 0.009, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.00023378913278157608, | |
| "loss": 0.01, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.0002330694494422454, | |
| "loss": 0.0093, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 0.00023234976610291472, | |
| "loss": 0.0089, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.000231630082763584, | |
| "loss": 0.0098, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.0002309103994242533, | |
| "loss": 0.0101, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.0002301907160849226, | |
| "loss": 0.0094, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.00022947103274559194, | |
| "loss": 0.0092, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 0.00022875134940626124, | |
| "loss": 0.0102, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.00022803166606693052, | |
| "loss": 0.0091, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 0.00022731198272759982, | |
| "loss": 0.0095, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.00022659229938826913, | |
| "loss": 0.0094, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.00022587261604893846, | |
| "loss": 0.0091, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 0.00022515293270960777, | |
| "loss": 0.0099, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.00022443324937027707, | |
| "loss": 0.0103, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 0.00022371356603094635, | |
| "loss": 0.0103, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 0.00022299388269161565, | |
| "loss": 0.0105, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.00022227419935228498, | |
| "loss": 0.0097, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.0002215545160129543, | |
| "loss": 0.0099, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.0002208348326736236, | |
| "loss": 0.0099, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.00022011514933429287, | |
| "loss": 0.0099, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.00021939546599496218, | |
| "loss": 0.0093, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.0002186757826556315, | |
| "loss": 0.0091, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 0.00021795609931630081, | |
| "loss": 0.0096, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 0.00021723641597697012, | |
| "loss": 0.0103, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.00021651673263763942, | |
| "loss": 0.0095, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 0.0002157970492983087, | |
| "loss": 0.0104, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.00021507736595897803, | |
| "loss": 0.009, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.00021435768261964734, | |
| "loss": 0.0097, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_bleu": 41.3133, | |
| "eval_gen_len": 13.0472, | |
| "eval_loss": 0.01007869653403759, | |
| "eval_runtime": 1065.665, | |
| "eval_samples_per_second": 12.419, | |
| "eval_steps_per_second": 6.209, | |
| "step": 59550 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 0.00021363799928031664, | |
| "loss": 0.0073, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 0.00021291831594098595, | |
| "loss": 0.0066, | |
| "step": 60500 | |
| } | |
| ], | |
| "max_steps": 208425, | |
| "num_train_epochs": 7, | |
| "total_flos": 6.31369374988032e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |