| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.133744855967078, | |
| "eval_steps": 25, | |
| "global_step": 23, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.13168724279835392, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.13168724279835392, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.4871, | |
| "eval_samples_per_second": 33.622, | |
| "eval_steps_per_second": 8.742, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.26337448559670784, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.5267489711934157, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.6584362139917695, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.571489144483944e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.9218106995884774, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.095061449516903e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 1.0884773662551441, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.570292669790186e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.2201646090534979, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.006958254769438e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.3518518518518519, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.415552058736854e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.4835390946502058, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.80709086014102e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.6152263374485596, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.192909139858981e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.7469135802469136, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.584447941263149e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.8786008230452675, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9930417452305626e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 2.045267489711934, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4297073302098156e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 2.1769547325102883, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9049385504830985e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 2.308641975308642, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4285108555160577e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 2.4403292181069958, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0092991918301108e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 2.57201646090535, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6551126795408016e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 2.7037037037037037, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3725491432254624e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.8353909465020575, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1668722069349041e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 3.0020576131687244, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0419132428365116e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 3.133744855967078, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 23, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.886664174203044e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |