{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.5020080321285141, "eval_steps": 200, "global_step": 1000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.10040160642570281, "eval_loss": NaN, "eval_runtime": 211.1229, "eval_samples_per_second": 25.488, "eval_steps_per_second": 1.596, "eval_wer": 1.0, "step": 200 }, { "epoch": 0.20080321285140562, "eval_loss": NaN, "eval_runtime": 210.3593, "eval_samples_per_second": 25.58, "eval_steps_per_second": 1.602, "eval_wer": 1.0, "step": 400 }, { "epoch": 0.25100401606425704, "grad_norm": NaN, "learning_rate": 0.0, "loss": 0.0, "step": 500 }, { "epoch": 0.30120481927710846, "eval_loss": NaN, "eval_runtime": 208.2843, "eval_samples_per_second": 25.835, "eval_steps_per_second": 1.618, "eval_wer": 1.0, "step": 600 }, { "epoch": 0.40160642570281124, "eval_loss": NaN, "eval_runtime": 209.206, "eval_samples_per_second": 25.721, "eval_steps_per_second": 1.611, "eval_wer": 1.0, "step": 800 }, { "epoch": 0.5020080321285141, "grad_norm": NaN, "learning_rate": 0.0, "loss": 0.0, "step": 1000 }, { "epoch": 0.5020080321285141, "eval_loss": NaN, "eval_runtime": 209.1208, "eval_samples_per_second": 25.732, "eval_steps_per_second": 1.612, "eval_wer": 1.0, "step": 1000 }, { "epoch": 0.5020080321285141, "step": 1000, "total_flos": 1.9194706730546028e+18, "train_loss": 0.0, "train_runtime": 2166.6734, "train_samples_per_second": 1.846, "train_steps_per_second": 0.462 } ], "logging_steps": 500, "max_steps": 1000, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 200, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1.9194706730546028e+18, "train_batch_size": 4, "trial_name": null, "trial_params": null }