{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.010893246187363835, "eval_steps": 3, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0010893246187363835, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.0010893246187363835, "eval_loss": NaN, "eval_runtime": 9.224, "eval_samples_per_second": 41.956, "eval_steps_per_second": 21.032, "step": 1 }, { "epoch": 0.002178649237472767, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.0032679738562091504, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.0032679738562091504, "eval_loss": NaN, "eval_runtime": 7.9067, "eval_samples_per_second": 48.946, "eval_steps_per_second": 24.536, "step": 3 }, { "epoch": 0.004357298474945534, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.0054466230936819175, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 5 }, { "epoch": 0.006535947712418301, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.006535947712418301, "eval_loss": NaN, "eval_runtime": 8.1166, "eval_samples_per_second": 47.68, "eval_steps_per_second": 23.902, "step": 6 }, { "epoch": 0.007625272331154684, "grad_norm": NaN, "learning_rate": 0.00014, "loss": 0.0, "step": 7 }, { "epoch": 0.008714596949891068, "grad_norm": NaN, "learning_rate": 0.00016, "loss": 0.0, "step": 8 }, { "epoch": 0.00980392156862745, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.00980392156862745, "eval_loss": NaN, "eval_runtime": 7.9625, "eval_samples_per_second": 48.603, "eval_steps_per_second": 24.364, "step": 9 }, { "epoch": 0.010893246187363835, "grad_norm": NaN, "learning_rate": 0.0002, "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": 90150544343040.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }