{ "best_metric": 3.872448444366455, "best_model_checkpoint": "/Users/frapadovani/Desktop/babyLM_controlled/models_trained/reduce_on_plateau_convergence/age_random/checkpoint-6000", "epoch": 0.03174922346690937, "eval_steps": 2000, "global_step": 6000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.010583074488969791, "grad_norm": 1.3282362222671509, "learning_rate": 0.0001, "loss": 4.8574, "step": 2000 }, { "epoch": 0.010583074488969791, "eval_loss": 4.1984477043151855, "eval_runtime": 2.3492, "eval_samples_per_second": 744.941, "eval_steps_per_second": 46.825, "step": 2000 }, { "epoch": 0.021166148977939583, "grad_norm": 1.406479835510254, "learning_rate": 0.0001, "loss": 4.145, "step": 4000 }, { "epoch": 0.021166148977939583, "eval_loss": 3.9832916259765625, "eval_runtime": 2.1928, "eval_samples_per_second": 798.069, "eval_steps_per_second": 50.164, "step": 4000 }, { "epoch": 0.03174922346690937, "grad_norm": 1.4979146718978882, "learning_rate": 0.0001, "loss": 3.9948, "step": 6000 }, { "epoch": 0.03174922346690937, "eval_loss": 3.872448444366455, "eval_runtime": 2.0908, "eval_samples_per_second": 837.0, "eval_steps_per_second": 52.611, "step": 6000 } ], "logging_steps": 2000, "max_steps": 188981, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 2000, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 3, "early_stopping_threshold": 0.001 }, "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": 58491666432000.0, "train_batch_size": 16, "trial_name": null, "trial_params": null }