{ "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": 641.732177734375, "learning_rate": 4.0000000000000003e-07, "loss": 8.8563, "step": 10 }, { "epoch": 0.0010578512396694215, "grad_norm": 167.62478637695312, "learning_rate": 1.2000000000000002e-06, "loss": 8.669, "step": 20 }, { "epoch": 0.0015867768595041322, "grad_norm": 132.942138671875, "learning_rate": 2.0000000000000003e-06, "loss": 8.4099, "step": 30 }, { "epoch": 0.002115702479338843, "grad_norm": 87.03181457519531, "learning_rate": 2.8000000000000003e-06, "loss": 8.3399, "step": 40 }, { "epoch": 0.002644628099173554, "grad_norm": 83.94163513183594, "learning_rate": 3.6e-06, "loss": 8.4131, "step": 50 }, { "epoch": 0.0031735537190082643, "grad_norm": 224.91473388671875, "learning_rate": 4.4e-06, "loss": 8.1753, "step": 60 }, { "epoch": 0.0037024793388429752, "grad_norm": 316.9183044433594, "learning_rate": 5.2e-06, "loss": 8.411, "step": 70 }, { "epoch": 0.004231404958677686, "grad_norm": 344.9347839355469, "learning_rate": 6e-06, "loss": 8.2236, "step": 80 }, { "epoch": 0.004760330578512397, "grad_norm": 131.94554138183594, "learning_rate": 6.800000000000001e-06, "loss": 8.2993, "step": 90 }, { "epoch": 0.005289256198347108, "grad_norm": 187.1765594482422, "learning_rate": 7.6e-06, "loss": 8.0748, "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": 1698066208358400.0, "train_batch_size": 8, "trial_name": null, "trial_params": null }