| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 3804, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.026288117770767613, | |
| "grad_norm": 0.21158406138420105, | |
| "learning_rate": 6.377383300460224e-07, | |
| "loss": 3.4637, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.052576235541535225, | |
| "grad_norm": 0.17568713426589966, | |
| "learning_rate": 1.2886259040105195e-06, | |
| "loss": 3.5087, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.07886435331230283, | |
| "grad_norm": 0.6034949421882629, | |
| "learning_rate": 1.946088099934254e-06, | |
| "loss": 3.4185, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.10515247108307045, | |
| "grad_norm": 0.34301501512527466, | |
| "learning_rate": 2.603550295857988e-06, | |
| "loss": 3.2854, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.13144058885383805, | |
| "grad_norm": 3.483755588531494, | |
| "learning_rate": 3.2610124917817228e-06, | |
| "loss": 3.1951, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.15772870662460567, | |
| "grad_norm": 0.43615999817848206, | |
| "learning_rate": 3.918474687705457e-06, | |
| "loss": 3.0889, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.18401682439537329, | |
| "grad_norm": 0.3760946989059448, | |
| "learning_rate": 4.575936883629192e-06, | |
| "loss": 2.8217, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.2103049421661409, | |
| "grad_norm": 0.2940825819969177, | |
| "learning_rate": 5.2333990795529265e-06, | |
| "loss": 2.5901, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.23659305993690852, | |
| "grad_norm": 0.38412269949913025, | |
| "learning_rate": 5.89086127547666e-06, | |
| "loss": 2.5224, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.2628811777076761, | |
| "grad_norm": 0.25396350026130676, | |
| "learning_rate": 6.548323471400395e-06, | |
| "loss": 2.4714, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.2891692954784437, | |
| "grad_norm": 0.21601170301437378, | |
| "learning_rate": 7.20578566732413e-06, | |
| "loss": 2.457, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.31545741324921134, | |
| "grad_norm": 0.23218804597854614, | |
| "learning_rate": 7.863247863247863e-06, | |
| "loss": 2.4262, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.34174553101997895, | |
| "grad_norm": 0.24238590896129608, | |
| "learning_rate": 8.5207100591716e-06, | |
| "loss": 2.4206, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.36803364879074657, | |
| "grad_norm": 0.4151826500892639, | |
| "learning_rate": 9.178172255095332e-06, | |
| "loss": 2.3889, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.3943217665615142, | |
| "grad_norm": 0.22028537094593048, | |
| "learning_rate": 9.835634451019067e-06, | |
| "loss": 2.377, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.4206098843322818, | |
| "grad_norm": 0.23977142572402954, | |
| "learning_rate": 1.0493096646942801e-05, | |
| "loss": 2.3533, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.4468980021030494, | |
| "grad_norm": 0.2686922252178192, | |
| "learning_rate": 1.1150558842866538e-05, | |
| "loss": 2.3217, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.47318611987381703, | |
| "grad_norm": 0.2237405776977539, | |
| "learning_rate": 1.1808021038790272e-05, | |
| "loss": 2.3034, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.49947423764458465, | |
| "grad_norm": 0.35920849442481995, | |
| "learning_rate": 1.2465483234714005e-05, | |
| "loss": 2.296, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.5257623554153522, | |
| "grad_norm": 0.32759296894073486, | |
| "learning_rate": 1.312294543063774e-05, | |
| "loss": 2.291, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.5520504731861199, | |
| "grad_norm": 0.3541663587093353, | |
| "learning_rate": 1.3780407626561474e-05, | |
| "loss": 2.2739, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.5783385909568874, | |
| "grad_norm": 0.3697475492954254, | |
| "learning_rate": 1.4437869822485209e-05, | |
| "loss": 2.2553, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.6046267087276551, | |
| "grad_norm": 0.27857789397239685, | |
| "learning_rate": 1.5095332018408943e-05, | |
| "loss": 2.2625, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.6309148264984227, | |
| "grad_norm": 0.22623978555202484, | |
| "learning_rate": 1.5752794214332678e-05, | |
| "loss": 2.2512, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.6572029442691903, | |
| "grad_norm": 0.3197992146015167, | |
| "learning_rate": 1.641025641025641e-05, | |
| "loss": 2.222, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.6834910620399579, | |
| "grad_norm": 0.2565959692001343, | |
| "learning_rate": 1.7067718606180147e-05, | |
| "loss": 2.2295, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.7097791798107256, | |
| "grad_norm": 0.24300645291805267, | |
| "learning_rate": 1.772518080210388e-05, | |
| "loss": 2.217, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.7360672975814931, | |
| "grad_norm": 0.21543020009994507, | |
| "learning_rate": 1.8382642998027616e-05, | |
| "loss": 2.234, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.7623554153522608, | |
| "grad_norm": 0.27316907048225403, | |
| "learning_rate": 1.904010519395135e-05, | |
| "loss": 2.2144, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.7886435331230284, | |
| "grad_norm": 0.3314705789089203, | |
| "learning_rate": 1.9697567389875082e-05, | |
| "loss": 2.2068, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.814931650893796, | |
| "grad_norm": 0.2859819531440735, | |
| "learning_rate": 1.975319567905163e-05, | |
| "loss": 2.1974, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.8412197686645636, | |
| "grad_norm": 0.44442227482795715, | |
| "learning_rate": 1.8051220835680475e-05, | |
| "loss": 2.1802, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.8675078864353313, | |
| "grad_norm": 0.35564538836479187, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 2.1839, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.8937960042060988, | |
| "grad_norm": 0.28175088763237, | |
| "learning_rate": 1.1110865250488047e-05, | |
| "loss": 2.1736, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.9200841219768665, | |
| "grad_norm": 0.28838351368904114, | |
| "learning_rate": 7.0355686110209266e-06, | |
| "loss": 2.1717, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.9463722397476341, | |
| "grad_norm": 0.3840157687664032, | |
| "learning_rate": 3.4570596330386775e-06, | |
| "loss": 2.1674, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.9726603575184016, | |
| "grad_norm": 0.2805449366569519, | |
| "learning_rate": 9.750348092257368e-07, | |
| "loss": 2.1741, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.9989484752891693, | |
| "grad_norm": 0.3055085837841034, | |
| "learning_rate": 5.438766451707489e-09, | |
| "loss": 2.1764, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 3804, | |
| "total_flos": 5.5431121920956826e+17, | |
| "train_loss": 2.4680882914209215, | |
| "train_runtime": 1212.9814, | |
| "train_samples_per_second": 50.165, | |
| "train_steps_per_second": 3.136 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 3804, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.5431121920956826e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |