{ "best_metric": null, "best_model_checkpoint": null, "epoch": 63999.000000520835, "eval_steps": 500, "global_step": 1000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 6399.000000520833, "grad_norm": 4.542983151623048e-05, "learning_rate": 4.9833333333333336e-05, "loss": 0.1489, "step": 100 }, { "epoch": 12799.000000520833, "grad_norm": 4.029877527500503e-05, "learning_rate": 4.966666666666667e-05, "loss": 0.0, "step": 200 }, { "epoch": 19199.000000520835, "grad_norm": 2.9974760309414705e-06, "learning_rate": 4.9500000000000004e-05, "loss": 0.0, "step": 300 }, { "epoch": 25599.000000520835, "grad_norm": 2.9752829959761584e-06, "learning_rate": 4.933333333333334e-05, "loss": 0.0, "step": 400 }, { "epoch": 31999.000000520835, "grad_norm": 2.955280251626391e-06, "learning_rate": 4.9166666666666665e-05, "loss": 0.0, "step": 500 }, { "epoch": 38399.000000520835, "grad_norm": 2.9332441044971347e-06, "learning_rate": 4.9e-05, "loss": 0.0, "step": 600 }, { "epoch": 44799.000000520835, "grad_norm": 2.89548052023747e-06, "learning_rate": 4.883333333333334e-05, "loss": 0.0, "step": 700 }, { "epoch": 51199.000000520835, "grad_norm": 2.890284349632566e-06, "learning_rate": 4.866666666666667e-05, "loss": 0.0, "step": 800 }, { "epoch": 57599.000000520835, "grad_norm": 1.1434361368856116e-07, "learning_rate": 4.85e-05, "loss": 0.0, "step": 900 }, { "epoch": 63999.000000520835, "grad_norm": 1.1111468722901918e-07, "learning_rate": 4.8333333333333334e-05, "loss": 0.0, "step": 1000 } ], "logging_steps": 100, "max_steps": 30000, "num_input_tokens_seen": 0, "num_train_epochs": 9223372036854775807, "save_steps": 1000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 433564876800000.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }