{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 25, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.04, "grad_norm": 52.35670654945737, "learning_rate": 6.666666666666667e-06, "loss": 1.1797, "step": 1 }, { "epoch": 0.2, "grad_norm": 78.00343229930253, "learning_rate": 1.9594929736144978e-05, "loss": 1.3873, "step": 5 }, { "epoch": 0.4, "grad_norm": 14.842921808281147, "learning_rate": 1.5406408174555978e-05, "loss": 1.2452, "step": 10 }, { "epoch": 0.6, "grad_norm": 5.790210129797682, "learning_rate": 8.576851617267151e-06, "loss": 0.9707, "step": 15 }, { "epoch": 0.8, "grad_norm": 3.7307757411742117, "learning_rate": 2.4425042564574186e-06, "loss": 0.81, "step": 20 }, { "epoch": 1.0, "grad_norm": 2.349583644410224, "learning_rate": 0.0, "loss": 0.7412, "step": 25 }, { "epoch": 1.0, "eval_loss": 0.7393369078636169, "eval_runtime": 15.2556, "eval_samples_per_second": 9.374, "eval_steps_per_second": 0.328, "step": 25 }, { "epoch": 1.0, "step": 25, "total_flos": 2617245696000.0, "train_loss": 1.022568130493164, "train_runtime": 720.6069, "train_samples_per_second": 1.106, "train_steps_per_second": 0.035 } ], "logging_steps": 5, "max_steps": 25, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 800, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 2617245696000.0, "train_batch_size": 8, "trial_name": null, "trial_params": null }