{ "best_metric": null, "best_model_checkpoint": null, "epoch": 4.60377358490566, "eval_steps": 500, "global_step": 30, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.1509433962264151, "grad_norm": 13.165218608472474, "learning_rate": 4.986304738420684e-06, "loss": 0.9079, "step": 1 }, { "epoch": 0.7547169811320755, "grad_norm": 17.002498641555743, "learning_rate": 4.665063509461098e-06, "loss": 0.5612, "step": 5 }, { "epoch": 1.5283018867924527, "grad_norm": 1.5923825945506376, "learning_rate": 3.7500000000000005e-06, "loss": 0.2763, "step": 10 }, { "epoch": 2.30188679245283, "grad_norm": 1.0761593457168466, "learning_rate": 2.5e-06, "loss": 0.2326, "step": 15 }, { "epoch": 3.0754716981132075, "grad_norm": 1.2810570431761181, "learning_rate": 1.2500000000000007e-06, "loss": 0.2069, "step": 20 }, { "epoch": 3.830188679245283, "grad_norm": 0.7326663835650753, "learning_rate": 3.3493649053890325e-07, "loss": 0.1744, "step": 25 }, { "epoch": 4.60377358490566, "grad_norm": 0.6162448672162039, "learning_rate": 0.0, "loss": 0.1789, "step": 30 }, { "epoch": 4.60377358490566, "step": 30, "total_flos": 4199089930240.0, "train_loss": 0.28329702814420066, "train_runtime": 654.1509, "train_samples_per_second": 3.241, "train_steps_per_second": 0.046 } ], "logging_steps": 5, "max_steps": 30, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": false, "should_training_stop": false }, "attributes": {} } }, "total_flos": 4199089930240.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }