{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.43883708173340646, "eval_steps": 10, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00877674163466813, "eval_loss": NaN, "eval_runtime": 27.3419, "eval_samples_per_second": 28.089, "eval_steps_per_second": 3.511, "step": 1 }, { "epoch": 0.0877674163466813, "grad_norm": NaN, "learning_rate": 9.330127018922194e-05, "loss": 0.0, "step": 10 }, { "epoch": 0.0877674163466813, "eval_loss": NaN, "eval_runtime": 26.7826, "eval_samples_per_second": 28.675, "eval_steps_per_second": 3.584, "step": 10 }, { "epoch": 0.1755348326933626, "grad_norm": NaN, "learning_rate": 6.91341716182545e-05, "loss": 0.0, "step": 20 }, { "epoch": 0.1755348326933626, "eval_loss": NaN, "eval_runtime": 26.5791, "eval_samples_per_second": 28.895, "eval_steps_per_second": 3.612, "step": 20 }, { "epoch": 0.2633022490400439, "grad_norm": NaN, "learning_rate": 3.705904774487396e-05, "loss": 0.0, "step": 30 }, { "epoch": 0.2633022490400439, "eval_loss": NaN, "eval_runtime": 26.6585, "eval_samples_per_second": 28.809, "eval_steps_per_second": 3.601, "step": 30 }, { "epoch": 0.3510696653867252, "grad_norm": NaN, "learning_rate": 1.0332332985438248e-05, "loss": 0.0, "step": 40 }, { "epoch": 0.3510696653867252, "eval_loss": NaN, "eval_runtime": 26.5981, "eval_samples_per_second": 28.874, "eval_steps_per_second": 3.609, "step": 40 }, { "epoch": 0.43883708173340646, "grad_norm": NaN, "learning_rate": 0.0, "loss": 0.0, "step": 50 }, { "epoch": 0.43883708173340646, "eval_loss": NaN, "eval_runtime": 26.5901, "eval_samples_per_second": 28.883, "eval_steps_per_second": 3.61, "step": 50 } ], "logging_steps": 10, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 13, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 7.34826558652416e+16, "train_batch_size": 8, "trial_name": null, "trial_params": null }