| { | |
| "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": 8.229718208312988, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 2.0524, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.018656716417910446, | |
| "grad_norm": 8.02374267578125, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 2.0234, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03731343283582089, | |
| "grad_norm": 3.9405264854431152, | |
| "learning_rate": 7.407407407407407e-05, | |
| "loss": 1.762, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.055970149253731345, | |
| "grad_norm": 2.4330053329467773, | |
| "learning_rate": 0.00011111111111111112, | |
| "loss": 1.4793, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07462686567164178, | |
| "grad_norm": 1.2707175016403198, | |
| "learning_rate": 0.00014814814814814815, | |
| "loss": 1.3111, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09328358208955224, | |
| "grad_norm": 1.004278540611267, | |
| "learning_rate": 0.0001851851851851852, | |
| "loss": 1.2074, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11194029850746269, | |
| "grad_norm": 0.7126164436340332, | |
| "learning_rate": 0.00019992354201925428, | |
| "loss": 1.1125, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.13059701492537312, | |
| "grad_norm": 0.5630809664726257, | |
| "learning_rate": 0.0001994567221375987, | |
| "loss": 1.0635, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.14925373134328357, | |
| "grad_norm": 0.5791023373603821, | |
| "learning_rate": 0.00019856753906964686, | |
| "loss": 1.0219, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.16791044776119404, | |
| "grad_norm": 1.550959587097168, | |
| "learning_rate": 0.00019725976891203376, | |
| "loss": 0.9986, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1865671641791045, | |
| "grad_norm": 0.5787221193313599, | |
| "learning_rate": 0.00019553896537655318, | |
| "loss": 0.9727, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.20522388059701493, | |
| "grad_norm": 0.5211277604103088, | |
| "learning_rate": 0.0001934124362051919, | |
| "loss": 0.9605, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.22388059701492538, | |
| "grad_norm": 0.46695733070373535, | |
| "learning_rate": 0.000190889212136318, | |
| "loss": 0.9695, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.24253731343283583, | |
| "grad_norm": 0.48995310068130493, | |
| "learning_rate": 0.0001879800085538147, | |
| "loss": 0.9485, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.26119402985074625, | |
| "grad_norm": 0.8782228231430054, | |
| "learning_rate": 0.00018469717998202462, | |
| "loss": 0.9413, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.2798507462686567, | |
| "grad_norm": 0.7073250412940979, | |
| "learning_rate": 0.00018105466761975109, | |
| "loss": 0.9221, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.29850746268656714, | |
| "grad_norm": 0.8044834136962891, | |
| "learning_rate": 0.00017706794013612364, | |
| "loss": 0.9363, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.31716417910447764, | |
| "grad_norm": 0.6230499744415283, | |
| "learning_rate": 0.00017275392797975032, | |
| "loss": 0.9444, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.3358208955223881, | |
| "grad_norm": 0.4618063271045685, | |
| "learning_rate": 0.0001681309514801265, | |
| "loss": 0.9384, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.35447761194029853, | |
| "grad_norm": 0.4851289689540863, | |
| "learning_rate": 0.00016321864304663173, | |
| "loss": 0.9228, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.373134328358209, | |
| "grad_norm": 0.5840283036231995, | |
| "learning_rate": 0.0001580378637955128, | |
| "loss": 0.9308, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3917910447761194, | |
| "grad_norm": 1.0067591667175293, | |
| "learning_rate": 0.00015261061495891345, | |
| "loss": 0.9239, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.41044776119402987, | |
| "grad_norm": 0.5790657997131348, | |
| "learning_rate": 0.00014695994445216985, | |
| "loss": 0.909, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.4291044776119403, | |
| "grad_norm": 0.7979658246040344, | |
| "learning_rate": 0.00014110984899615367, | |
| "loss": 0.9051, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.44776119402985076, | |
| "grad_norm": 0.9141942262649536, | |
| "learning_rate": 0.000135085172210319, | |
| "loss": 0.9136, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.4664179104477612, | |
| "grad_norm": 0.527861475944519, | |
| "learning_rate": 0.00012891149910922267, | |
| "loss": 0.9185, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.48507462686567165, | |
| "grad_norm": 0.6267244815826416, | |
| "learning_rate": 0.00012261504745055964, | |
| "loss": 0.9016, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.503731343283582, | |
| "grad_norm": 0.5699637532234192, | |
| "learning_rate": 0.00011622255639612554, | |
| "loss": 0.8951, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.5223880597014925, | |
| "grad_norm": 1.0421922206878662, | |
| "learning_rate": 0.00010976117295853154, | |
| "loss": 0.9031, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.5410447761194029, | |
| "grad_norm": 0.5656252503395081, | |
| "learning_rate": 0.00010325833671589687, | |
| "loss": 0.9076, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.5597014925373134, | |
| "grad_norm": 0.5329589247703552, | |
| "learning_rate": 9.674166328410318e-05, | |
| "loss": 0.8981, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.5783582089552238, | |
| "grad_norm": 0.628094494342804, | |
| "learning_rate": 9.023882704146848e-05, | |
| "loss": 0.8999, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.5970149253731343, | |
| "grad_norm": 0.5785563588142395, | |
| "learning_rate": 8.377744360387447e-05, | |
| "loss": 0.8872, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.6156716417910447, | |
| "grad_norm": 0.5400257706642151, | |
| "learning_rate": 7.738495254944042e-05, | |
| "loss": 0.8889, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.6343283582089553, | |
| "grad_norm": 0.5926158428192139, | |
| "learning_rate": 7.108850089077735e-05, | |
| "loss": 0.8956, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.6529850746268657, | |
| "grad_norm": 0.8232181668281555, | |
| "learning_rate": 6.491482778968104e-05, | |
| "loss": 0.8931, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.6716417910447762, | |
| "grad_norm": 0.5512446761131287, | |
| "learning_rate": 5.889015100384636e-05, | |
| "loss": 0.8651, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.6902985074626866, | |
| "grad_norm": 0.5381608009338379, | |
| "learning_rate": 5.304005554783015e-05, | |
| "loss": 0.8817, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.7089552238805971, | |
| "grad_norm": 0.5687859058380127, | |
| "learning_rate": 4.738938504108659e-05, | |
| "loss": 0.8818, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.7276119402985075, | |
| "grad_norm": 0.5281744599342346, | |
| "learning_rate": 4.196213620448723e-05, | |
| "loss": 0.8795, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.746268656716418, | |
| "grad_norm": 0.5830202102661133, | |
| "learning_rate": 3.6781356953368284e-05, | |
| "loss": 0.8769, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.7649253731343284, | |
| "grad_norm": 0.6224981546401978, | |
| "learning_rate": 3.186904851987351e-05, | |
| "loss": 0.8821, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.7835820895522388, | |
| "grad_norm": 0.5855913758277893, | |
| "learning_rate": 2.724607202024969e-05, | |
| "loss": 0.883, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.8022388059701493, | |
| "grad_norm": 0.5719298720359802, | |
| "learning_rate": 2.2932059863876365e-05, | |
| "loss": 0.8909, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.8208955223880597, | |
| "grad_norm": 0.5183894038200378, | |
| "learning_rate": 1.8945332380248913e-05, | |
| "loss": 0.8782, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.8395522388059702, | |
| "grad_norm": 0.5395970344543457, | |
| "learning_rate": 1.5302820017975394e-05, | |
| "loss": 0.8847, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.8582089552238806, | |
| "grad_norm": 0.5199528336524963, | |
| "learning_rate": 1.2019991446185309e-05, | |
| "loss": 0.889, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.8768656716417911, | |
| "grad_norm": 0.5345931053161621, | |
| "learning_rate": 9.110787863682002e-06, | |
| "loss": 0.8732, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.8955223880597015, | |
| "grad_norm": 0.5364944338798523, | |
| "learning_rate": 6.587563794808127e-06, | |
| "loss": 0.8651, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.914179104477612, | |
| "grad_norm": 0.5282942056655884, | |
| "learning_rate": 4.461034623446847e-06, | |
| "loss": 0.895, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.9328358208955224, | |
| "grad_norm": 0.5484575033187866, | |
| "learning_rate": 2.7402310879662497e-06, | |
| "loss": 0.8827, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.9514925373134329, | |
| "grad_norm": 0.5638120770454407, | |
| "learning_rate": 1.43246093035313e-06, | |
| "loss": 0.8804, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.9701492537313433, | |
| "grad_norm": 0.5108746290206909, | |
| "learning_rate": 5.432778624013257e-07, | |
| "loss": 0.8699, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.9888059701492538, | |
| "grad_norm": 0.52601557970047, | |
| "learning_rate": 7.645798074572552e-08, | |
| "loss": 0.8838, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.4824345111846924, | |
| "eval_runtime": 0.929, | |
| "eval_samples_per_second": 2.153, | |
| "eval_steps_per_second": 1.076, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 268, | |
| "total_flos": 3.7501312597753856e+17, | |
| "train_loss": 0.975214945736216, | |
| "train_runtime": 1874.6509, | |
| "train_samples_per_second": 4.569, | |
| "train_steps_per_second": 0.143 | |
| } | |
| ], | |
| "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": 3.7501312597753856e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |