| { |
| "best_metric": 0.8531136389750661, |
| "best_model_checkpoint": "../../checkpoint/unlearn_cl/imdb/electra-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": 0.914, |
| "dt_accuracy": 0.899, |
| "epoch": 1.0, |
| "eval_accuracy": 0.899, |
| "eval_loss": 0.3365958333015442, |
| "eval_runtime": 39.7879, |
| "eval_samples_per_second": 628.331, |
| "eval_steps_per_second": 2.463, |
| "eval_unlearn_overall_accuracy": 0.7361297725426482, |
| "step": 782, |
| "unlearn_overall_accuracy": 0.7361297725426482, |
| "unlearn_time": null |
| }, |
| { |
| "epoch": 1.278772378516624, |
| "grad_norm": 1.0107311010360718, |
| "learning_rate": 3.934356351236147e-05, |
| "loss": 0.1081, |
| "step": 1000 |
| }, |
| { |
| "df_accuracy": 0.824, |
| "dt_accuracy": 0.89888, |
| "epoch": 2.0, |
| "eval_accuracy": 0.89888, |
| "eval_loss": 0.33242085576057434, |
| "eval_runtime": 39.662, |
| "eval_samples_per_second": 630.327, |
| "eval_steps_per_second": 2.471, |
| "eval_unlearn_overall_accuracy": 0.8032644395878864, |
| "step": 1564, |
| "unlearn_overall_accuracy": 0.8032644395878864, |
| "unlearn_time": null |
| }, |
| { |
| "epoch": 2.557544757033248, |
| "grad_norm": 0.37590524554252625, |
| "learning_rate": 2.8687127024722932e-05, |
| "loss": 0.09, |
| "step": 2000 |
| }, |
| { |
| "df_accuracy": 0.752, |
| "dt_accuracy": 0.90192, |
| "epoch": 3.0, |
| "eval_accuracy": 0.90192, |
| "eval_loss": 0.3572903871536255, |
| "eval_runtime": 39.6917, |
| "eval_samples_per_second": 629.855, |
| "eval_steps_per_second": 2.469, |
| "eval_unlearn_overall_accuracy": 0.8531136389750661, |
| "step": 2346, |
| "unlearn_overall_accuracy": 0.8531136389750661, |
| "unlearn_time": null |
| }, |
| { |
| "epoch": 3.836317135549872, |
| "grad_norm": 1.6976776123046875, |
| "learning_rate": 1.80306905370844e-05, |
| "loss": 0.0754, |
| "step": 3000 |
| }, |
| { |
| "df_accuracy": 0.396, |
| "dt_accuracy": 0.89184, |
| "epoch": 4.0, |
| "eval_accuracy": 0.89184, |
| "eval_loss": 0.4108133316040039, |
| "eval_runtime": 39.7241, |
| "eval_samples_per_second": 629.342, |
| "eval_steps_per_second": 2.467, |
| "eval_unlearn_overall_accuracy": 0, |
| "step": 3128, |
| "unlearn_overall_accuracy": 0, |
| "unlearn_time": null |
| }, |
| { |
| "df_accuracy": 0.252, |
| "dt_accuracy": 0.8986, |
| "epoch": 5.0, |
| "eval_accuracy": 0.8986, |
| "eval_loss": 0.44819915294647217, |
| "eval_runtime": 39.6814, |
| "eval_samples_per_second": 630.018, |
| "eval_steps_per_second": 2.47, |
| "eval_unlearn_overall_accuracy": 0, |
| "step": 3910, |
| "unlearn_overall_accuracy": 0, |
| "unlearn_time": null |
| }, |
| { |
| "epoch": 5.115089514066496, |
| "grad_norm": 0.8873926401138306, |
| "learning_rate": 7.374254049445865e-06, |
| "loss": 0.046, |
| "step": 4000 |
| }, |
| { |
| "df_accuracy": 0.212, |
| "dt_accuracy": 0.8964, |
| "epoch": 6.0, |
| "eval_accuracy": 0.8964, |
| "eval_loss": 0.5018645524978638, |
| "eval_runtime": 39.6772, |
| "eval_samples_per_second": 630.084, |
| "eval_steps_per_second": 2.47, |
| "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": 0.0721028426317506, |
| "train_runtime": 1086.5889, |
| "train_samples_per_second": 138.047, |
| "train_steps_per_second": 4.318 |
| } |
| ], |
| "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 |
| } |
|
|
