| { | |
| "best_metric": 0.01884845644235611, | |
| "best_model_checkpoint": "./results/checkpoint-4500", | |
| "epoch": 0.9439899307740718, | |
| "global_step": 4500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.9300748199426614e-05, | |
| "loss": 0.0391, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_accuracy": 0.990558615263572, | |
| "eval_loss": 0.04349859058856964, | |
| "eval_runtime": 154.2476, | |
| "eval_samples_per_second": 123.6, | |
| "eval_steps_per_second": 7.728, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.860149639885323e-05, | |
| "loss": 0.0327, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_accuracy": 0.9903488067138736, | |
| "eval_loss": 0.04805811867117882, | |
| "eval_runtime": 154.05, | |
| "eval_samples_per_second": 123.759, | |
| "eval_steps_per_second": 7.738, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.790224459827984e-05, | |
| "loss": 0.0266, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_accuracy": 0.9911355887752425, | |
| "eval_loss": 0.0459710918366909, | |
| "eval_runtime": 154.4944, | |
| "eval_samples_per_second": 123.403, | |
| "eval_steps_per_second": 7.715, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.7202992797706454e-05, | |
| "loss": 0.035, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_accuracy": 0.9916601101494886, | |
| "eval_loss": 0.03351669758558273, | |
| "eval_runtime": 154.0214, | |
| "eval_samples_per_second": 123.782, | |
| "eval_steps_per_second": 7.739, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 1.650374099713307e-05, | |
| "loss": 0.0371, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_accuracy": 0.9930763178599528, | |
| "eval_loss": 0.025116313248872757, | |
| "eval_runtime": 153.2057, | |
| "eval_samples_per_second": 124.441, | |
| "eval_steps_per_second": 7.78, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1.580448919655968e-05, | |
| "loss": 0.026, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_accuracy": 0.9938630999213218, | |
| "eval_loss": 0.027913494035601616, | |
| "eval_runtime": 153.7631, | |
| "eval_samples_per_second": 123.989, | |
| "eval_steps_per_second": 7.752, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.5105237395986297e-05, | |
| "loss": 0.0299, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_accuracy": 0.9934959349593496, | |
| "eval_loss": 0.027549268677830696, | |
| "eval_runtime": 153.8917, | |
| "eval_samples_per_second": 123.886, | |
| "eval_steps_per_second": 7.746, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.4405985595412911e-05, | |
| "loss": 0.0254, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_accuracy": 0.9945449777078416, | |
| "eval_loss": 0.024684084579348564, | |
| "eval_runtime": 153.4415, | |
| "eval_samples_per_second": 124.249, | |
| "eval_steps_per_second": 7.768, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.3706733794839521e-05, | |
| "loss": 0.0219, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_accuracy": 0.9954366640440598, | |
| "eval_loss": 0.01884845644235611, | |
| "eval_runtime": 153.901, | |
| "eval_samples_per_second": 123.878, | |
| "eval_steps_per_second": 7.745, | |
| "step": 4500 | |
| } | |
| ], | |
| "max_steps": 14301, | |
| "num_train_epochs": 3, | |
| "total_flos": 9537652703232000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |