| { | |
| "best_metric": 0.42561376094818115, | |
| "best_model_checkpoint": "bert_base_lda_100_v1_sst2/checkpoint-264", | |
| "epoch": 6.0, | |
| "eval_steps": 500, | |
| "global_step": 1584, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 5.9014997482299805, | |
| "learning_rate": 4.9e-05, | |
| "loss": 0.3965, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8096330275229358, | |
| "eval_loss": 0.42561376094818115, | |
| "eval_runtime": 0.5929, | |
| "eval_samples_per_second": 1470.729, | |
| "eval_steps_per_second": 6.746, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 9.258822441101074, | |
| "learning_rate": 4.8e-05, | |
| "loss": 0.2228, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8130733944954128, | |
| "eval_loss": 0.5018868446350098, | |
| "eval_runtime": 0.5813, | |
| "eval_samples_per_second": 1499.991, | |
| "eval_steps_per_second": 6.881, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 5.464596271514893, | |
| "learning_rate": 4.7e-05, | |
| "loss": 0.1618, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7740825688073395, | |
| "eval_loss": 0.65505450963974, | |
| "eval_runtime": 0.5745, | |
| "eval_samples_per_second": 1517.95, | |
| "eval_steps_per_second": 6.963, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 6.5892815589904785, | |
| "learning_rate": 4.600000000000001e-05, | |
| "loss": 0.1246, | |
| "step": 1056 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8153669724770642, | |
| "eval_loss": 0.6144545078277588, | |
| "eval_runtime": 0.5638, | |
| "eval_samples_per_second": 1546.748, | |
| "eval_steps_per_second": 7.095, | |
| "step": 1056 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 2.094468593597412, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.0947, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.8096330275229358, | |
| "eval_loss": 0.5503551959991455, | |
| "eval_runtime": 0.5693, | |
| "eval_samples_per_second": 1531.819, | |
| "eval_steps_per_second": 7.027, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 8.200359344482422, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 0.0757, | |
| "step": 1584 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.8142201834862385, | |
| "eval_loss": 0.6799033880233765, | |
| "eval_runtime": 0.5981, | |
| "eval_samples_per_second": 1458.036, | |
| "eval_steps_per_second": 6.688, | |
| "step": 1584 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "step": 1584, | |
| "total_flos": 5.316079940232192e+16, | |
| "train_loss": 0.1793321395161176, | |
| "train_runtime": 671.0754, | |
| "train_samples_per_second": 5017.991, | |
| "train_steps_per_second": 19.67 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 13200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 50, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 5 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.316079940232192e+16, | |
| "train_batch_size": 256, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |