{ "best_metric": 108.55545060029843, "best_model_checkpoint": "./models/rootflo/fauna-v3.2/checkpoint-460", "epoch": 1.0, "eval_steps": 500, "global_step": 460, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.43478260869565216, "grad_norm": 0.5209075808525085, "learning_rate": 1.9919182516351267e-06, "loss": 0.4607, "step": 200 }, { "epoch": 0.8695652173913043, "grad_norm": 0.5061023235321045, "learning_rate": 1.955244232925309e-06, "loss": 0.2067, "step": 400 }, { "epoch": 1.0, "eval_loss": 0.08908500522375107, "eval_runtime": 28373.2469, "eval_samples_per_second": 1.383, "eval_steps_per_second": 0.004, "eval_wer": 108.55545060029843, "step": 460 } ], "logging_steps": 200, "max_steps": 3680, "num_input_tokens_seen": 0, "num_train_epochs": 8, "save_steps": 500, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 3, "early_stopping_threshold": 0.01 }, "attributes": { "early_stopping_patience_counter": 0 } }, "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 1.2002681817409278e+21, "train_batch_size": 96, "trial_name": null, "trial_params": null }