{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 0.001322314049586777, "eval_steps": 500, "global_step": 100, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0001322314049586777, "grad_norm": 242.3459014892578, "learning_rate": 4.0000000000000003e-07, "loss": 9.4189, "step": 10 }, { "epoch": 0.0002644628099173554, "grad_norm": 111.8305435180664, "learning_rate": 1.2000000000000002e-06, "loss": 9.7941, "step": 20 }, { "epoch": 0.00039669421487603304, "grad_norm": 40.939884185791016, "learning_rate": 2.0000000000000003e-06, "loss": 9.6039, "step": 30 }, { "epoch": 0.0005289256198347108, "grad_norm": 26.80072593688965, "learning_rate": 2.8000000000000003e-06, "loss": 9.3667, "step": 40 }, { "epoch": 0.0006611570247933885, "grad_norm": 19.54555320739746, "learning_rate": 3.6e-06, "loss": 9.4609, "step": 50 }, { "epoch": 0.0007933884297520661, "grad_norm": 25.509206771850586, "learning_rate": 4.4e-06, "loss": 9.6385, "step": 60 }, { "epoch": 0.0009256198347107438, "grad_norm": 15.738627433776855, "learning_rate": 5.2e-06, "loss": 9.4883, "step": 70 }, { "epoch": 0.0010578512396694215, "grad_norm": 17.5339412689209, "learning_rate": 6e-06, "loss": 9.1943, "step": 80 }, { "epoch": 0.0011900826446280992, "grad_norm": 30.582969665527344, "learning_rate": 6.800000000000001e-06, "loss": 9.3046, "step": 90 }, { "epoch": 0.001322314049586777, "grad_norm": 25.765249252319336, "learning_rate": 7.6e-06, "loss": 9.253, "step": 100 } ], "logging_steps": 10, "max_steps": 10000000, "num_input_tokens_seen": 0, "num_train_epochs": 133, "save_steps": 100, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 442615400448000.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }