| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.1, |
| "eval_steps": 100.0, |
| "global_step": 100, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.001, |
| "grad_norm": 43.548129517838454, |
| "learning_rate": 1.0000000000000002e-06, |
| "loss": 4.1920576095581055, |
| "step": 1, |
| "token_acc": 0.34359059658460855 |
| }, |
| { |
| "epoch": 0.005, |
| "grad_norm": 14.427483007671363, |
| "learning_rate": 5e-06, |
| "loss": 2.9412002563476562, |
| "step": 5, |
| "token_acc": 0.512452240845581 |
| }, |
| { |
| "epoch": 0.01, |
| "grad_norm": 7.934074490008561, |
| "learning_rate": 1e-05, |
| "loss": 2.503311347961426, |
| "step": 10, |
| "token_acc": 0.5123253736192332 |
| }, |
| { |
| "epoch": 0.015, |
| "grad_norm": 2.5682097340060643, |
| "learning_rate": 9.999370638369377e-06, |
| "loss": 1.8719802856445313, |
| "step": 15, |
| "token_acc": 0.6410698878343399 |
| }, |
| { |
| "epoch": 0.02, |
| "grad_norm": 3.0601891911453225, |
| "learning_rate": 9.997482711915926e-06, |
| "loss": 1.7852279663085937, |
| "step": 20, |
| "token_acc": 0.6242933840865835 |
| }, |
| { |
| "epoch": 0.025, |
| "grad_norm": 2.9591215037175895, |
| "learning_rate": 9.994336695915041e-06, |
| "loss": 1.6610099792480468, |
| "step": 25, |
| "token_acc": 0.6568298460323727 |
| }, |
| { |
| "epoch": 0.03, |
| "grad_norm": 2.3839735362461623, |
| "learning_rate": 9.989933382359423e-06, |
| "loss": 1.6115425109863282, |
| "step": 30, |
| "token_acc": 0.6632120451693851 |
| }, |
| { |
| "epoch": 0.035, |
| "grad_norm": 2.0296518100505776, |
| "learning_rate": 9.984273879759713e-06, |
| "loss": 1.7307615280151367, |
| "step": 35, |
| "token_acc": 0.6267176116002563 |
| }, |
| { |
| "epoch": 0.04, |
| "grad_norm": 2.274063193212189, |
| "learning_rate": 9.977359612865424e-06, |
| "loss": 1.6226930618286133, |
| "step": 40, |
| "token_acc": 0.6632471264367816 |
| }, |
| { |
| "epoch": 0.045, |
| "grad_norm": 1.995496122888669, |
| "learning_rate": 9.969192322306271e-06, |
| "loss": 1.6562419891357423, |
| "step": 45, |
| "token_acc": 0.6479170419164758 |
| }, |
| { |
| "epoch": 0.05, |
| "grad_norm": 2.030243788478171, |
| "learning_rate": 9.959774064153977e-06, |
| "loss": 1.5927490234375, |
| "step": 50, |
| "token_acc": 0.6578526695879487 |
| }, |
| { |
| "epoch": 0.055, |
| "grad_norm": 1.913105067952688, |
| "learning_rate": 9.949107209404664e-06, |
| "loss": 1.886464500427246, |
| "step": 55, |
| "token_acc": 0.5819125113628805 |
| }, |
| { |
| "epoch": 0.06, |
| "grad_norm": 1.8949380801330526, |
| "learning_rate": 9.937194443381972e-06, |
| "loss": 1.6359737396240235, |
| "step": 60, |
| "token_acc": 0.6552567735622108 |
| }, |
| { |
| "epoch": 0.065, |
| "grad_norm": 1.4853873443995649, |
| "learning_rate": 9.924038765061042e-06, |
| "loss": 1.3352900505065919, |
| "step": 65, |
| "token_acc": 0.7206670637284097 |
| }, |
| { |
| "epoch": 0.07, |
| "grad_norm": 1.6844968929576292, |
| "learning_rate": 9.909643486313533e-06, |
| "loss": 1.4845345497131348, |
| "step": 70, |
| "token_acc": 0.6865343744776369 |
| }, |
| { |
| "epoch": 0.075, |
| "grad_norm": 1.7982742317399707, |
| "learning_rate": 9.894012231073895e-06, |
| "loss": 1.5165021896362305, |
| "step": 75, |
| "token_acc": 0.6689946239260413 |
| }, |
| { |
| "epoch": 0.08, |
| "grad_norm": 1.7083434381167786, |
| "learning_rate": 9.877148934427037e-06, |
| "loss": 1.501682949066162, |
| "step": 80, |
| "token_acc": 0.6582693568920952 |
| }, |
| { |
| "epoch": 0.085, |
| "grad_norm": 2.276089893387222, |
| "learning_rate": 9.859057841617709e-06, |
| "loss": 1.3892568588256835, |
| "step": 85, |
| "token_acc": 0.7173441424982873 |
| }, |
| { |
| "epoch": 0.09, |
| "grad_norm": 3.2510132262305955, |
| "learning_rate": 9.839743506981783e-06, |
| "loss": 1.6044925689697265, |
| "step": 90, |
| "token_acc": 0.6260809087747768 |
| }, |
| { |
| "epoch": 0.095, |
| "grad_norm": 2.3567789267765544, |
| "learning_rate": 9.819210792799711e-06, |
| "loss": 1.531374168395996, |
| "step": 95, |
| "token_acc": 0.661787561762045 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 1.7140659626033266, |
| "learning_rate": 9.797464868072489e-06, |
| "loss": 1.636698341369629, |
| "step": 100, |
| "token_acc": 0.6505466960542806 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 1000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 9223372036854775807, |
| "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": 93095931019264.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
