{ "best_metric": null, "best_model_checkpoint": null, "epoch": 4.966740576496674, "eval_steps": 500, "global_step": 560, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.8869179600886918, "grad_norm": 9.466493606567383, "learning_rate": 1e-05, "loss": 10.3156, "step": 100 }, { "epoch": 1.7738359201773837, "grad_norm": 6.788516998291016, "learning_rate": 2e-05, "loss": 3.112, "step": 200 }, { "epoch": 2.6607538802660753, "grad_norm": 2.6718461513519287, "learning_rate": 3e-05, "loss": 2.9775, "step": 300 }, { "epoch": 3.5476718403547673, "grad_norm": 11.880657196044922, "learning_rate": 4e-05, "loss": 2.2977, "step": 400 }, { "epoch": 4.434589800443459, "grad_norm": 20.061622619628906, "learning_rate": 5e-05, "loss": 0.7123, "step": 500 }, { "epoch": 4.434589800443459, "eval_loss": 0.31634521484375, "eval_runtime": 137.1888, "eval_samples_per_second": 3.273, "eval_steps_per_second": 0.824, "eval_wer": 0.15710892432982695, "step": 500 }, { "epoch": 4.966740576496674, "step": 560, "total_flos": 1.7812856904421847e+18, "train_loss": 3.520488684517997, "train_runtime": 16100.7223, "train_samples_per_second": 1.12, "train_steps_per_second": 0.035 }, { "epoch": 4.966740576496674, "eval_loss": 0.23389407992362976, "eval_runtime": 140.2305, "eval_samples_per_second": 3.166, "eval_steps_per_second": 0.792, "eval_wer": 0.12748344370860928, "step": 560 } ], "logging_steps": 100, "max_steps": 560, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 2000, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 3, "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": 1.7812856904421847e+18, "train_batch_size": 8, "trial_name": null, "trial_params": null }