| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.99972833469166, | |
| "global_step": 230, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00035999999999999997, | |
| "loss": 0.2157, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0005999707572027913, | |
| "loss": 0.2186, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0005995322292545942, | |
| "loss": 0.2325, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0005985682199945492, | |
| "loss": 0.2308, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.000597080420622471, | |
| "loss": 0.236, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0005950714412440158, | |
| "loss": 0.2367, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0005925448062916689, | |
| "loss": 0.2416, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0005895049483416934, | |
| "loss": 0.2413, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.000585957200337884, | |
| "loss": 0.2479, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0005819077862357724, | |
| "loss": 0.2352, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0005773638100836939, | |
| "loss": 0.2438, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0005723332435598725, | |
| "loss": 0.2371, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0005668249119873892, | |
| "loss": 0.2392, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0005608484788515657, | |
| "loss": 0.2229, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.0005544144288469277, | |
| "loss": 0.2289, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0005475340494834885, | |
| "loss": 0.2342, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00054021941128462, | |
| "loss": 0.2318, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0005324833466112538, | |
| "loss": 0.2189, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0005243394271495595, | |
| "loss": 0.2193, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.0005158019401015953, | |
| "loss": 0.2233, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.0005068858631207009, | |
| "loss": 0.2111, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0004976068380356041, | |
| "loss": 0.2166, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00048798114340933813, | |
| "loss": 0.2088, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.0004780256659811104, | |
| "loss": 0.2029, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00046775787104122397, | |
| "loss": 0.2072, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.00045719577179102375, | |
| "loss": 0.2002, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.0004463578977416198, | |
| "loss": 0.202, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.0004352632622068292, | |
| "loss": 0.1967, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.0004239313289473625, | |
| "loss": 0.1939, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.0004123819780247736, | |
| "loss": 0.1905, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.0004006354709250765, | |
| "loss": 0.1853, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.000388712415013214, | |
| "loss": 0.1809, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.0003766337273807371, | |
| "loss": 0.177, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.00036442059815011896, | |
| "loss": 0.1808, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.0003520944533000791, | |
| "loss": 0.1707, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.00033967691707713674, | |
| "loss": 0.172, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.0003271897740593341, | |
| "loss": 0.1632, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.000314654930938684, | |
| "loss": 0.1734, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_gen_len": 122.123, | |
| "eval_loss": 1.8751367330551147, | |
| "eval_rouge1": 57.9286, | |
| "eval_rouge2": 29.2743, | |
| "eval_rougeL": 44.7181, | |
| "eval_rougeLsum": 54.2295, | |
| "eval_runtime": 1692.8237, | |
| "eval_samples_per_second": 0.591, | |
| "eval_steps_per_second": 0.148, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.00030209437808938845, | |
| "loss": 0.1607, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.0002895301509892498, | |
| "loss": 0.1423, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0002769842915619544, | |
| "loss": 0.1361, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.0002644788095080497, | |
| "loss": 0.1438, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.00025203564369244956, | |
| "loss": 0.1367, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.00023967662365621063, | |
| "loss": 0.1333, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.0002274234313200997, | |
| "loss": 0.1325, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.000215297562947137, | |
| "loss": 0.1367, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.00020332029143084668, | |
| "loss": 0.1309, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.00019151262897537235, | |
| "loss": 0.1356, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.00017989529023293153, | |
| "loss": 0.128, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.00016848865596327673, | |
| "loss": 0.1215, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.0001573127372789174, | |
| "loss": 0.1244, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.00014638714053882856, | |
| "loss": 0.1265, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.00013573103295223495, | |
| "loss": 0.117, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.0001253631089528132, | |
| "loss": 0.1216, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 0.0001153015574023025, | |
| "loss": 0.1157, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 0.00010556402968106073, | |
| "loss": 0.1197, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 9.616760872154511e-05, | |
| "loss": 0.1227, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 8.712877903904379e-05, | |
| "loss": 0.1156, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 7.846339781223482e-05, | |
| "loss": 0.1198, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 7.018666706430662e-05, | |
| "loss": 0.1192, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 6.231310699344282e-05, | |
| "loss": 0.116, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 5.485653049946145e-05, | |
| "loss": 0.119, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 4.7830018951294724e-05, | |
| "loss": 0.1135, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 4.124589923782276e-05, | |
| "loss": 0.1169, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 3.51157221423219e-05, | |
| "loss": 0.115, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 2.945024207846589e-05, | |
| "loss": 0.1156, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 2.425939822342968e-05, | |
| "loss": 0.1157, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 1.9552297081195668e-05, | |
| "loss": 0.1136, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 1.5337196506651038e-05, | |
| "loss": 0.111, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 1.162149121850433e-05, | |
| "loss": 0.113, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 8.411699826436147e-06, | |
| "loss": 0.1098, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 5.7134533952425395e-06, | |
| "loss": 0.1111, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 3.5314855660341646e-06, | |
| "loss": 0.1098, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 1.869624251821089e-06, | |
| "loss": 0.1111, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 7.307849220527406e-07, | |
| "loss": 0.1121, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 1.1696548789369431e-07, | |
| "loss": 0.1098, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_gen_len": 122.364, | |
| "eval_loss": 2.1311135292053223, | |
| "eval_rouge1": 58.1114, | |
| "eval_rouge2": 29.339, | |
| "eval_rougeL": 44.7611, | |
| "eval_rougeLsum": 54.2823, | |
| "eval_runtime": 1701.9255, | |
| "eval_samples_per_second": 0.588, | |
| "eval_steps_per_second": 0.147, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 230, | |
| "total_flos": 2.7141869303916134e+17, | |
| "train_loss": 0.16691997828690902, | |
| "train_runtime": 19759.1358, | |
| "train_samples_per_second": 2.98, | |
| "train_steps_per_second": 0.012 | |
| } | |
| ], | |
| "max_steps": 230, | |
| "num_train_epochs": 2, | |
| "total_flos": 2.7141869303916134e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |