| { |
| "best_metric": 0.9721505009154305, |
| "best_model_checkpoint": "../../checkpoint/unlearn/imdb/bert-base/random_label/2.0/42/checkpoint-2346", |
| "epoch": 6.0, |
| "eval_steps": 500, |
| "global_step": 4692, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "df_accuracy": 0.9, |
| "dt_accuracy": 0.87568, |
| "epoch": 1.0, |
| "eval_accuracy": 0.87568, |
| "eval_loss": 0.48319077491760254, |
| "eval_runtime": 38.8105, |
| "eval_samples_per_second": 644.155, |
| "eval_steps_per_second": 2.525, |
| "eval_unlearn_overall_accuracy": 0.7470558631102164, |
| "step": 782, |
| "unlearn_overall_accuracy": 0.7470558631102164, |
| "unlearn_time": null |
| }, |
| { |
| "epoch": 1.278772378516624, |
| "grad_norm": 0.6550465226173401, |
| "learning_rate": 3.934356351236147e-05, |
| "loss": 0.1211, |
| "step": 1000 |
| }, |
| { |
| "df_accuracy": 0.686, |
| "dt_accuracy": 0.85736, |
| "epoch": 2.0, |
| "eval_accuracy": 0.85736, |
| "eval_loss": 0.524350106716156, |
| "eval_runtime": 38.2794, |
| "eval_samples_per_second": 653.092, |
| "eval_steps_per_second": 2.56, |
| "eval_unlearn_overall_accuracy": 0.8857119555475892, |
| "step": 1564, |
| "unlearn_overall_accuracy": 0.8857119555475892, |
| "unlearn_time": null |
| }, |
| { |
| "epoch": 2.557544757033248, |
| "grad_norm": 1.059643268585205, |
| "learning_rate": 2.8687127024722932e-05, |
| "loss": 0.0966, |
| "step": 2000 |
| }, |
| { |
| "df_accuracy": 0.536, |
| "dt_accuracy": 0.86652, |
| "epoch": 3.0, |
| "eval_accuracy": 0.86652, |
| "eval_loss": 0.5727993845939636, |
| "eval_runtime": 37.5173, |
| "eval_samples_per_second": 666.36, |
| "eval_steps_per_second": 2.612, |
| "eval_unlearn_overall_accuracy": 0.9721505009154305, |
| "step": 2346, |
| "unlearn_overall_accuracy": 0.9721505009154305, |
| "unlearn_time": null |
| }, |
| { |
| "epoch": 3.836317135549872, |
| "grad_norm": 0.3413985073566437, |
| "learning_rate": 1.80306905370844e-05, |
| "loss": 0.0615, |
| "step": 3000 |
| }, |
| { |
| "df_accuracy": 0.202, |
| "dt_accuracy": 0.87016, |
| "epoch": 4.0, |
| "eval_accuracy": 0.87016, |
| "eval_loss": 0.7414253354072571, |
| "eval_runtime": 38.1255, |
| "eval_samples_per_second": 655.73, |
| "eval_steps_per_second": 2.57, |
| "eval_unlearn_overall_accuracy": 0, |
| "step": 3128, |
| "unlearn_overall_accuracy": 0, |
| "unlearn_time": null |
| }, |
| { |
| "df_accuracy": 0.06, |
| "dt_accuracy": 0.86636, |
| "epoch": 5.0, |
| "eval_accuracy": 0.86636, |
| "eval_loss": 0.9550507068634033, |
| "eval_runtime": 37.4988, |
| "eval_samples_per_second": 666.688, |
| "eval_steps_per_second": 2.613, |
| "eval_unlearn_overall_accuracy": 0, |
| "step": 3910, |
| "unlearn_overall_accuracy": 0, |
| "unlearn_time": null |
| }, |
| { |
| "epoch": 5.115089514066496, |
| "grad_norm": 0.035878658294677734, |
| "learning_rate": 7.374254049445865e-06, |
| "loss": 0.0257, |
| "step": 4000 |
| }, |
| { |
| "df_accuracy": 0.028, |
| "dt_accuracy": 0.86524, |
| "epoch": 6.0, |
| "eval_accuracy": 0.86524, |
| "eval_loss": 1.0964415073394775, |
| "eval_runtime": 37.4104, |
| "eval_samples_per_second": 668.264, |
| "eval_steps_per_second": 2.62, |
| "eval_unlearn_overall_accuracy": 0, |
| "step": 4692, |
| "unlearn_overall_accuracy": 0, |
| "unlearn_time": null |
| }, |
| { |
| "epoch": 6.0, |
| "step": 4692, |
| "total_flos": 9866664576000000.0, |
| "train_loss": 0.06626078021495849, |
| "train_runtime": 1044.1712, |
| "train_samples_per_second": 143.655, |
| "train_steps_per_second": 4.494 |
| } |
| ], |
| "logging_steps": 1000, |
| "max_steps": 4692, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 6, |
| "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": 9866664576000000.0, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
