| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.976501305483029, | |
| "eval_steps": 500, | |
| "global_step": 285, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05221932114882506, | |
| "grad_norm": 4.916470527648926, | |
| "learning_rate": 4.996203791083291e-05, | |
| "loss": 3.0294, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.10443864229765012, | |
| "grad_norm": 2.873619318008423, | |
| "learning_rate": 4.984826693294874e-05, | |
| "loss": 2.7312, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1566579634464752, | |
| "grad_norm": 1.968766689300537, | |
| "learning_rate": 4.965903258506806e-05, | |
| "loss": 2.6282, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.20887728459530025, | |
| "grad_norm": 2.165731430053711, | |
| "learning_rate": 4.9394909565685894e-05, | |
| "loss": 2.5533, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.26109660574412535, | |
| "grad_norm": 2.0350794792175293, | |
| "learning_rate": 4.905670000773126e-05, | |
| "loss": 2.5412, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3133159268929504, | |
| "grad_norm": 1.8538161516189575, | |
| "learning_rate": 4.864543104251587e-05, | |
| "loss": 2.5643, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.36553524804177545, | |
| "grad_norm": 1.6806731224060059, | |
| "learning_rate": 4.8162351680370044e-05, | |
| "loss": 2.5158, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4177545691906005, | |
| "grad_norm": 1.7877177000045776, | |
| "learning_rate": 4.760892901743944e-05, | |
| "loss": 2.5183, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4699738903394256, | |
| "grad_norm": 1.8654683828353882, | |
| "learning_rate": 4.698684378016222e-05, | |
| "loss": 2.496, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5221932114882507, | |
| "grad_norm": 1.7663869857788086, | |
| "learning_rate": 4.629798522095818e-05, | |
| "loss": 2.5069, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5744125326370757, | |
| "grad_norm": 1.914778470993042, | |
| "learning_rate": 4.554444538063113e-05, | |
| "loss": 2.4605, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.6266318537859008, | |
| "grad_norm": 1.7610474824905396, | |
| "learning_rate": 4.4728512734909844e-05, | |
| "loss": 2.4223, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.6788511749347258, | |
| "grad_norm": 1.6278265714645386, | |
| "learning_rate": 4.385266524442241e-05, | |
| "loss": 2.4468, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.7310704960835509, | |
| "grad_norm": 1.709999442100525, | |
| "learning_rate": 4.2919562829211283e-05, | |
| "loss": 2.3933, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.783289817232376, | |
| "grad_norm": 1.6477118730545044, | |
| "learning_rate": 4.193203929064353e-05, | |
| "loss": 2.454, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.835509138381201, | |
| "grad_norm": 1.584774136543274, | |
| "learning_rate": 4.089309370524921e-05, | |
| "loss": 2.4139, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.8877284595300261, | |
| "grad_norm": 1.5124833583831787, | |
| "learning_rate": 3.9805881316624506e-05, | |
| "loss": 2.3528, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.9399477806788512, | |
| "grad_norm": 1.6704648733139038, | |
| "learning_rate": 3.867370395306068e-05, | |
| "loss": 2.3643, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.9921671018276762, | |
| "grad_norm": 1.619065761566162, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 2.3584, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.0443864229765012, | |
| "grad_norm": 1.49176824092865, | |
| "learning_rate": 3.628833395777224e-05, | |
| "loss": 2.1535, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.0966057441253263, | |
| "grad_norm": 1.5439894199371338, | |
| "learning_rate": 3.504238561632424e-05, | |
| "loss": 2.0786, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.1488250652741514, | |
| "grad_norm": 1.5870767831802368, | |
| "learning_rate": 3.376593887981887e-05, | |
| "loss": 2.0251, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.2010443864229765, | |
| "grad_norm": 1.5849578380584717, | |
| "learning_rate": 3.246287027504237e-05, | |
| "loss": 2.0486, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.2532637075718016, | |
| "grad_norm": 1.5910005569458008, | |
| "learning_rate": 3.1137137178519985e-05, | |
| "loss": 2.003, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.3054830287206267, | |
| "grad_norm": 1.5487288236618042, | |
| "learning_rate": 2.9792765798093465e-05, | |
| "loss": 2.0196, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.3577023498694518, | |
| "grad_norm": 1.572863221168518, | |
| "learning_rate": 2.8433838945460205e-05, | |
| "loss": 1.9855, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.4099216710182767, | |
| "grad_norm": 1.5365219116210938, | |
| "learning_rate": 2.7064483636808313e-05, | |
| "loss": 2.0136, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.4621409921671018, | |
| "grad_norm": 1.619452714920044, | |
| "learning_rate": 2.5688858559204053e-05, | |
| "loss": 1.9636, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.514360313315927, | |
| "grad_norm": 1.5345263481140137, | |
| "learning_rate": 2.4311141440795953e-05, | |
| "loss": 1.9941, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.566579634464752, | |
| "grad_norm": 1.59757661819458, | |
| "learning_rate": 2.2935516363191693e-05, | |
| "loss": 1.9606, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.6187989556135771, | |
| "grad_norm": 1.493499994277954, | |
| "learning_rate": 2.1566161054539798e-05, | |
| "loss": 2.0351, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.671018276762402, | |
| "grad_norm": 1.5033268928527832, | |
| "learning_rate": 2.0207234201906547e-05, | |
| "loss": 1.9508, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.723237597911227, | |
| "grad_norm": 1.487410545349121, | |
| "learning_rate": 1.8862862821480025e-05, | |
| "loss": 1.9504, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.7754569190600522, | |
| "grad_norm": 1.6940875053405762, | |
| "learning_rate": 1.7537129724957642e-05, | |
| "loss": 1.9508, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.8276762402088773, | |
| "grad_norm": 1.555407166481018, | |
| "learning_rate": 1.6234061120181142e-05, | |
| "loss": 1.8806, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.8798955613577024, | |
| "grad_norm": 1.6240324974060059, | |
| "learning_rate": 1.495761438367577e-05, | |
| "loss": 1.9759, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.9321148825065273, | |
| "grad_norm": 1.5653289556503296, | |
| "learning_rate": 1.3711666042227772e-05, | |
| "loss": 1.9918, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.9843342036553526, | |
| "grad_norm": 1.5873417854309082, | |
| "learning_rate": 1.2500000000000006e-05, | |
| "loss": 1.8922, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.0365535248041775, | |
| "grad_norm": 1.4565200805664062, | |
| "learning_rate": 1.1326296046939333e-05, | |
| "loss": 1.7482, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 2.0887728459530024, | |
| "grad_norm": 1.5391967296600342, | |
| "learning_rate": 1.0194118683375503e-05, | |
| "loss": 1.6307, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.1409921671018277, | |
| "grad_norm": 1.497523307800293, | |
| "learning_rate": 9.106906294750805e-06, | |
| "loss": 1.6288, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 2.1932114882506526, | |
| "grad_norm": 1.5081855058670044, | |
| "learning_rate": 8.067960709356478e-06, | |
| "loss": 1.6239, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.245430809399478, | |
| "grad_norm": 1.4794273376464844, | |
| "learning_rate": 7.080437170788723e-06, | |
| "loss": 1.6385, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 2.297650130548303, | |
| "grad_norm": 1.590654730796814, | |
| "learning_rate": 6.147334755577596e-06, | |
| "loss": 1.6511, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.349869451697128, | |
| "grad_norm": 1.516768217086792, | |
| "learning_rate": 5.271487265090163e-06, | |
| "loss": 1.6356, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 2.402088772845953, | |
| "grad_norm": 1.5770176649093628, | |
| "learning_rate": 4.4555546193688735e-06, | |
| "loss": 1.6163, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.454308093994778, | |
| "grad_norm": 1.5710504055023193, | |
| "learning_rate": 3.7020147790418263e-06, | |
| "loss": 1.6386, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 2.506527415143603, | |
| "grad_norm": 1.5108474493026733, | |
| "learning_rate": 3.013156219837776e-06, | |
| "loss": 1.6722, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.558746736292428, | |
| "grad_norm": 1.5271434783935547, | |
| "learning_rate": 2.391070982560564e-06, | |
| "loss": 1.6134, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 2.6109660574412534, | |
| "grad_norm": 1.5538915395736694, | |
| "learning_rate": 1.837648319629956e-06, | |
| "loss": 1.6621, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.6631853785900783, | |
| "grad_norm": 1.4325404167175293, | |
| "learning_rate": 1.3545689574841342e-06, | |
| "loss": 1.5881, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 2.7154046997389036, | |
| "grad_norm": 1.505527138710022, | |
| "learning_rate": 9.432999922687396e-07, | |
| "loss": 1.6241, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.7676240208877285, | |
| "grad_norm": 1.491540789604187, | |
| "learning_rate": 6.050904343141095e-07, | |
| "loss": 1.5779, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 2.8198433420365534, | |
| "grad_norm": 1.508405327796936, | |
| "learning_rate": 3.4096741493194197e-07, | |
| "loss": 1.5785, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.8720626631853787, | |
| "grad_norm": 1.4897537231445312, | |
| "learning_rate": 1.517330670512629e-07, | |
| "loss": 1.6248, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 2.9242819843342036, | |
| "grad_norm": 1.4672536849975586, | |
| "learning_rate": 3.796208916709565e-08, | |
| "loss": 1.5898, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.976501305483029, | |
| "grad_norm": 1.4578866958618164, | |
| "learning_rate": 0.0, | |
| "loss": 1.5727, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 2.976501305483029, | |
| "step": 285, | |
| "total_flos": 1.0513138638127104e+17, | |
| "train_loss": 2.0445492710983544, | |
| "train_runtime": 467.486, | |
| "train_samples_per_second": 4.916, | |
| "train_steps_per_second": 0.61 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 285, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.0513138638127104e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |