{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 0.005289256198347108, "eval_steps": 500, "global_step": 100, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0005289256198347108, "grad_norm": 1352.7918701171875, "learning_rate": 3.2e-07, "loss": 8.1282, "step": 10 }, { "epoch": 0.0010578512396694215, "grad_norm": 157.71942138671875, "learning_rate": 1.12e-06, "loss": 8.0251, "step": 20 }, { "epoch": 0.0015867768595041322, "grad_norm": 122.08133697509766, "learning_rate": 1.92e-06, "loss": 7.8748, "step": 30 }, { "epoch": 0.002115702479338843, "grad_norm": 54.4079475402832, "learning_rate": 2.72e-06, "loss": 7.8115, "step": 40 }, { "epoch": 0.002644628099173554, "grad_norm": 48.29515838623047, "learning_rate": 3.52e-06, "loss": 7.8539, "step": 50 }, { "epoch": 0.0031735537190082643, "grad_norm": 105.55093383789062, "learning_rate": 4.32e-06, "loss": 7.7098, "step": 60 }, { "epoch": 0.0037024793388429752, "grad_norm": 96.70323181152344, "learning_rate": 5.12e-06, "loss": 7.8547, "step": 70 }, { "epoch": 0.004231404958677686, "grad_norm": 406.44293212890625, "learning_rate": 5.920000000000001e-06, "loss": 7.7145, "step": 80 }, { "epoch": 0.004760330578512397, "grad_norm": 240.23379516601562, "learning_rate": 6.72e-06, "loss": 7.7768, "step": 90 }, { "epoch": 0.005289256198347108, "grad_norm": 122.43266296386719, "learning_rate": 7.520000000000001e-06, "loss": 7.5916, "step": 100 } ], "logging_steps": 10, "max_steps": 10000000, "num_input_tokens_seen": 0, "num_train_epochs": 529, "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": 1740714979737600.0, "train_batch_size": 8, "trial_name": null, "trial_params": null }