| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 268, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0037313432835820895, | |
| "grad_norm": 7.512597560882568, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 2.0542, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.018656716417910446, | |
| "grad_norm": 7.686585426330566, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 2.0294, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03731343283582089, | |
| "grad_norm": 4.031171798706055, | |
| "learning_rate": 7.407407407407407e-05, | |
| "loss": 1.7759, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.055970149253731345, | |
| "grad_norm": 2.5195655822753906, | |
| "learning_rate": 0.00011111111111111112, | |
| "loss": 1.4858, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07462686567164178, | |
| "grad_norm": 1.1103084087371826, | |
| "learning_rate": 0.00014814814814814815, | |
| "loss": 1.3199, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09328358208955224, | |
| "grad_norm": 0.894225001335144, | |
| "learning_rate": 0.0001851851851851852, | |
| "loss": 1.213, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11194029850746269, | |
| "grad_norm": 1.1811108589172363, | |
| "learning_rate": 0.00019992354201925428, | |
| "loss": 1.1141, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.13059701492537312, | |
| "grad_norm": 0.6414879560470581, | |
| "learning_rate": 0.0001994567221375987, | |
| "loss": 1.064, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.14925373134328357, | |
| "grad_norm": 0.7366268634796143, | |
| "learning_rate": 0.00019856753906964686, | |
| "loss": 1.0217, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.16791044776119404, | |
| "grad_norm": 0.6300023198127747, | |
| "learning_rate": 0.00019725976891203376, | |
| "loss": 0.9985, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1865671641791045, | |
| "grad_norm": 0.5019010305404663, | |
| "learning_rate": 0.00019553896537655318, | |
| "loss": 0.9718, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.20522388059701493, | |
| "grad_norm": 0.5189563035964966, | |
| "learning_rate": 0.0001934124362051919, | |
| "loss": 0.9591, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.22388059701492538, | |
| "grad_norm": 0.5040785074234009, | |
| "learning_rate": 0.000190889212136318, | |
| "loss": 0.9711, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.24253731343283583, | |
| "grad_norm": 0.9470528364181519, | |
| "learning_rate": 0.0001879800085538147, | |
| "loss": 0.9512, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.26119402985074625, | |
| "grad_norm": 0.45922908186912537, | |
| "learning_rate": 0.00018469717998202462, | |
| "loss": 0.9433, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.2798507462686567, | |
| "grad_norm": 0.48557597398757935, | |
| "learning_rate": 0.00018105466761975109, | |
| "loss": 0.9228, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.29850746268656714, | |
| "grad_norm": 0.5197058916091919, | |
| "learning_rate": 0.00017706794013612364, | |
| "loss": 0.9366, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.31716417910447764, | |
| "grad_norm": 0.7142367362976074, | |
| "learning_rate": 0.00017275392797975032, | |
| "loss": 0.9464, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.3358208955223881, | |
| "grad_norm": 0.4473322927951813, | |
| "learning_rate": 0.0001681309514801265, | |
| "loss": 0.9397, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.35447761194029853, | |
| "grad_norm": 0.45314615964889526, | |
| "learning_rate": 0.00016321864304663173, | |
| "loss": 0.9241, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.373134328358209, | |
| "grad_norm": 0.5742659568786621, | |
| "learning_rate": 0.0001580378637955128, | |
| "loss": 0.9316, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3917910447761194, | |
| "grad_norm": 0.7061174511909485, | |
| "learning_rate": 0.00015261061495891345, | |
| "loss": 0.9249, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.41044776119402987, | |
| "grad_norm": 0.4923759996891022, | |
| "learning_rate": 0.00014695994445216985, | |
| "loss": 0.9111, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.4291044776119403, | |
| "grad_norm": 0.7759695649147034, | |
| "learning_rate": 0.00014110984899615367, | |
| "loss": 0.9068, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.44776119402985076, | |
| "grad_norm": 1.0017133951187134, | |
| "learning_rate": 0.000135085172210319, | |
| "loss": 0.9151, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.4664179104477612, | |
| "grad_norm": 0.564063310623169, | |
| "learning_rate": 0.00012891149910922267, | |
| "loss": 0.9197, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.48507462686567165, | |
| "grad_norm": 0.635895311832428, | |
| "learning_rate": 0.00012261504745055964, | |
| "loss": 0.9042, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.503731343283582, | |
| "grad_norm": 0.5336510539054871, | |
| "learning_rate": 0.00011622255639612554, | |
| "loss": 0.8974, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.5223880597014925, | |
| "grad_norm": 0.5803085565567017, | |
| "learning_rate": 0.00010976117295853154, | |
| "loss": 0.9051, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.5410447761194029, | |
| "grad_norm": 0.6651114821434021, | |
| "learning_rate": 0.00010325833671589687, | |
| "loss": 0.9099, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.5597014925373134, | |
| "grad_norm": 0.6448351740837097, | |
| "learning_rate": 9.674166328410318e-05, | |
| "loss": 0.8999, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.5783582089552238, | |
| "grad_norm": 0.5589825510978699, | |
| "learning_rate": 9.023882704146848e-05, | |
| "loss": 0.9023, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.5970149253731343, | |
| "grad_norm": 0.5227958559989929, | |
| "learning_rate": 8.377744360387447e-05, | |
| "loss": 0.8896, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.6156716417910447, | |
| "grad_norm": 0.5533550977706909, | |
| "learning_rate": 7.738495254944042e-05, | |
| "loss": 0.8908, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.6343283582089553, | |
| "grad_norm": 0.7187372446060181, | |
| "learning_rate": 7.108850089077735e-05, | |
| "loss": 0.8977, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.6529850746268657, | |
| "grad_norm": 0.6411680579185486, | |
| "learning_rate": 6.491482778968104e-05, | |
| "loss": 0.8956, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.6716417910447762, | |
| "grad_norm": 0.6200590133666992, | |
| "learning_rate": 5.889015100384636e-05, | |
| "loss": 0.8675, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.6902985074626866, | |
| "grad_norm": 0.5138359069824219, | |
| "learning_rate": 5.304005554783015e-05, | |
| "loss": 0.8836, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.7089552238805971, | |
| "grad_norm": 0.5824055075645447, | |
| "learning_rate": 4.738938504108659e-05, | |
| "loss": 0.8845, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.7276119402985075, | |
| "grad_norm": 0.5803791880607605, | |
| "learning_rate": 4.196213620448723e-05, | |
| "loss": 0.8813, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.746268656716418, | |
| "grad_norm": 0.5962420701980591, | |
| "learning_rate": 3.6781356953368284e-05, | |
| "loss": 0.879, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.7649253731343284, | |
| "grad_norm": 0.5040367245674133, | |
| "learning_rate": 3.186904851987351e-05, | |
| "loss": 0.8835, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.7835820895522388, | |
| "grad_norm": 0.5313622355461121, | |
| "learning_rate": 2.724607202024969e-05, | |
| "loss": 0.8852, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.8022388059701493, | |
| "grad_norm": 0.9790322780609131, | |
| "learning_rate": 2.2932059863876365e-05, | |
| "loss": 0.8931, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.8208955223880597, | |
| "grad_norm": 0.5015585422515869, | |
| "learning_rate": 1.8945332380248913e-05, | |
| "loss": 0.8808, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.8395522388059702, | |
| "grad_norm": 0.4975396990776062, | |
| "learning_rate": 1.5302820017975394e-05, | |
| "loss": 0.8867, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.8582089552238806, | |
| "grad_norm": 0.5071137547492981, | |
| "learning_rate": 1.2019991446185309e-05, | |
| "loss": 0.8919, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.8768656716417911, | |
| "grad_norm": 0.5157453417778015, | |
| "learning_rate": 9.110787863682002e-06, | |
| "loss": 0.8746, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.8955223880597015, | |
| "grad_norm": 0.5082049369812012, | |
| "learning_rate": 6.587563794808127e-06, | |
| "loss": 0.8678, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.914179104477612, | |
| "grad_norm": 0.5121915936470032, | |
| "learning_rate": 4.461034623446847e-06, | |
| "loss": 0.8979, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.9328358208955224, | |
| "grad_norm": 0.5356196761131287, | |
| "learning_rate": 2.7402310879662497e-06, | |
| "loss": 0.8849, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.9514925373134329, | |
| "grad_norm": 0.5412393808364868, | |
| "learning_rate": 1.43246093035313e-06, | |
| "loss": 0.8828, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.9701492537313433, | |
| "grad_norm": 0.5141103863716125, | |
| "learning_rate": 5.432778624013257e-07, | |
| "loss": 0.8721, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.9888059701492538, | |
| "grad_norm": 0.5164282917976379, | |
| "learning_rate": 7.645798074572552e-08, | |
| "loss": 0.8854, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.5774962902069092, | |
| "eval_runtime": 0.9281, | |
| "eval_samples_per_second": 2.155, | |
| "eval_steps_per_second": 1.077, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 268, | |
| "total_flos": 3.750133557582889e+17, | |
| "train_loss": 0.9775012651486183, | |
| "train_runtime": 1907.2727, | |
| "train_samples_per_second": 4.491, | |
| "train_steps_per_second": 0.141 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 268, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.750133557582889e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |