{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0013892747985551543, "eval_steps": 3, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0001389274798555154, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.0001389274798555154, "eval_loss": NaN, "eval_runtime": 82.2141, "eval_samples_per_second": 36.867, "eval_steps_per_second": 18.44, "step": 1 }, { "epoch": 0.0002778549597110308, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.0004167824395665463, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.0004167824395665463, "eval_loss": NaN, "eval_runtime": 67.5365, "eval_samples_per_second": 44.879, "eval_steps_per_second": 22.447, "step": 3 }, { "epoch": 0.0005557099194220616, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.0006946373992775772, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 5 }, { "epoch": 0.0008335648791330926, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.0008335648791330926, "eval_loss": NaN, "eval_runtime": 68.4341, "eval_samples_per_second": 44.291, "eval_steps_per_second": 22.153, "step": 6 }, { "epoch": 0.000972492358988608, "grad_norm": NaN, "learning_rate": 0.00014, "loss": 0.0, "step": 7 }, { "epoch": 0.0011114198388441233, "grad_norm": NaN, "learning_rate": 0.00016, "loss": 0.0, "step": 8 }, { "epoch": 0.0012503473186996387, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.0012503473186996387, "eval_loss": NaN, "eval_runtime": 68.9168, "eval_samples_per_second": 43.981, "eval_steps_per_second": 21.998, "step": 9 }, { "epoch": 0.0013892747985551543, "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": 48728898404352.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }