{ "best_metric": 1.7723504304885864, "best_model_checkpoint": "output/zemfira/checkpoint-49", "epoch": 1.0, "global_step": 49, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.1, "learning_rate": 0.00013370522424493186, "loss": 2.4725, "step": 5 }, { "epoch": 0.2, "learning_rate": 0.00012357697446014183, "loss": 2.1691, "step": 10 }, { "epoch": 0.31, "learning_rate": 0.00010784720288438084, "loss": 1.9883, "step": 15 }, { "epoch": 0.41, "learning_rate": 8.811859244288883e-05, "loss": 1.8517, "step": 20 }, { "epoch": 0.51, "learning_rate": 6.640126177858445e-05, "loss": 1.9739, "step": 25 }, { "epoch": 0.61, "learning_rate": 4.4907957266698305e-05, "loss": 1.9488, "step": 30 }, { "epoch": 0.71, "learning_rate": 2.5828599592490882e-05, "loss": 1.9148, "step": 35 }, { "epoch": 0.82, "learning_rate": 1.1107156004419736e-05, "loss": 1.9426, "step": 40 }, { "epoch": 0.92, "learning_rate": 2.24357239552258e-06, "loss": 2.0432, "step": 45 }, { "epoch": 1.0, "eval_loss": 1.7723504304885864, "eval_runtime": 3.4368, "eval_samples_per_second": 22.696, "eval_steps_per_second": 2.91, "step": 49 } ], "max_steps": 49, "num_train_epochs": 1, "total_flos": 50821300224000.0, "trial_name": null, "trial_params": null }