| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.020764119601328904, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008305647840531562, | |
| "grad_norm": 2.7521727085113525, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 2.8783, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008305647840531562, | |
| "eval_loss": 2.65358567237854, | |
| "eval_runtime": 71.8689, | |
| "eval_samples_per_second": 14.109, | |
| "eval_steps_per_second": 7.055, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016611295681063123, | |
| "grad_norm": 2.534353256225586, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 2.5571, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0024916943521594683, | |
| "grad_norm": 2.619391918182373, | |
| "learning_rate": 0.0001, | |
| "loss": 2.5198, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0033222591362126247, | |
| "grad_norm": 2.480504274368286, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 2.3843, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004152823920265781, | |
| "grad_norm": 2.3676488399505615, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 2.4082, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0049833887043189366, | |
| "grad_norm": 2.171743154525757, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.7348, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005813953488372093, | |
| "grad_norm": 2.1443028450012207, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 1.6026, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006644518272425249, | |
| "grad_norm": 2.2254693508148193, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 1.7396, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.007475083056478406, | |
| "grad_norm": 2.5551085472106934, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.0664, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.008305647840531562, | |
| "grad_norm": 2.318112373352051, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 1.6275, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009136212624584718, | |
| "grad_norm": 2.318878412246704, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 1.6692, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.009966777408637873, | |
| "grad_norm": 2.1796483993530273, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.6291, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01079734219269103, | |
| "grad_norm": 2.200101852416992, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 1.6143, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.011627906976744186, | |
| "grad_norm": 1.9241218566894531, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 1.4271, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.012458471760797342, | |
| "grad_norm": 2.12858510017395, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.6617, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.013289036544850499, | |
| "grad_norm": 2.173638343811035, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 1.746, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.014119601328903655, | |
| "grad_norm": 1.947255253791809, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 1.689, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.014950166112956811, | |
| "grad_norm": 2.135347604751587, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.0612, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.015780730897009966, | |
| "grad_norm": 1.937851071357727, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 1.8322, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.016611295681063124, | |
| "grad_norm": 2.0472640991210938, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 1.717, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01744186046511628, | |
| "grad_norm": 1.8501553535461426, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.6214, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.018272425249169437, | |
| "grad_norm": 1.7711646556854248, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 1.7159, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01910299003322259, | |
| "grad_norm": 2.242205858230591, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 1.7749, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.019933554817275746, | |
| "grad_norm": 1.9537017345428467, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.7306, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.020764119601328904, | |
| "grad_norm": 2.3009982109069824, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 1.8783, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.020764119601328904, | |
| "eval_loss": 2.0330841541290283, | |
| "eval_runtime": 71.4667, | |
| "eval_samples_per_second": 14.188, | |
| "eval_steps_per_second": 7.094, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5138718822236160.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |