{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.13157894736842105, "eval_steps": 3, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.013157894736842105, "grad_norm": NaN, "learning_rate": 1e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.013157894736842105, "eval_loss": NaN, "eval_runtime": 80.3177, "eval_samples_per_second": 1.606, "eval_steps_per_second": 0.809, "step": 1 }, { "epoch": 0.02631578947368421, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.039473684210526314, "grad_norm": NaN, "learning_rate": 3e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.039473684210526314, "eval_loss": NaN, "eval_runtime": 2.8056, "eval_samples_per_second": 45.979, "eval_steps_per_second": 23.168, "step": 3 }, { "epoch": 0.05263157894736842, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.06578947368421052, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.0, "step": 5 }, { "epoch": 0.07894736842105263, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 6 }, { "epoch": 0.07894736842105263, "eval_loss": NaN, "eval_runtime": 2.8248, "eval_samples_per_second": 45.668, "eval_steps_per_second": 23.011, "step": 6 }, { "epoch": 0.09210526315789473, "grad_norm": NaN, "learning_rate": 7e-05, "loss": 0.0, "step": 7 }, { "epoch": 0.10526315789473684, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 8 }, { "epoch": 0.11842105263157894, "grad_norm": NaN, "learning_rate": 9e-05, "loss": 0.0, "step": 9 }, { "epoch": 0.11842105263157894, "eval_loss": NaN, "eval_runtime": 2.8146, "eval_samples_per_second": 45.832, "eval_steps_per_second": 23.094, "step": 9 }, { "epoch": 0.13157894736842105, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 10 } ], "logging_steps": 1, "max_steps": 10, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 3, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 6514996968161280.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }