{ "best_metric": 2.904005527496338, "best_model_checkpoint": "PEFT/adapters-lib/output/mam/dataset-5100/test/checkpoint-1926", "epoch": 8.0, "eval_steps": 500, "global_step": 5136, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "eval_gen_len": 26.2222, "eval_loss": 3.184800863265991, "eval_rouge-1": 33.9748, "eval_rouge-2": 18.3088, "eval_rouge-l": 33.4231, "eval_runtime": 130.5235, "eval_samples_per_second": 3.448, "eval_steps_per_second": 0.437, "step": 642 }, { "epoch": 2.0, "eval_gen_len": 20.3911, "eval_loss": 3.0025367736816406, "eval_rouge-1": 37.1532, "eval_rouge-2": 19.9004, "eval_rouge-l": 36.5443, "eval_runtime": 108.9318, "eval_samples_per_second": 4.131, "eval_steps_per_second": 0.523, "step": 1284 }, { "epoch": 3.0, "eval_gen_len": 19.3489, "eval_loss": 2.904005527496338, "eval_rouge-1": 39.3585, "eval_rouge-2": 22.1712, "eval_rouge-l": 38.6987, "eval_runtime": 101.7517, "eval_samples_per_second": 4.423, "eval_steps_per_second": 0.56, "step": 1926 }, { "epoch": 4.0, "eval_gen_len": 19.2956, "eval_loss": 2.9436676502227783, "eval_rouge-1": 39.0962, "eval_rouge-2": 21.9264, "eval_rouge-l": 38.3542, "eval_runtime": 102.5418, "eval_samples_per_second": 4.388, "eval_steps_per_second": 0.556, "step": 2568 }, { "epoch": 5.0, "eval_gen_len": 17.7667, "eval_loss": 2.945244312286377, "eval_rouge-1": 38.377, "eval_rouge-2": 21.3498, "eval_rouge-l": 37.5445, "eval_runtime": 96.4996, "eval_samples_per_second": 4.663, "eval_steps_per_second": 0.591, "step": 3210 }, { "epoch": 6.0, "eval_gen_len": 19.7756, "eval_loss": 2.973095178604126, "eval_rouge-1": 37.8249, "eval_rouge-2": 21.0556, "eval_rouge-l": 37.3231, "eval_runtime": 102.758, "eval_samples_per_second": 4.379, "eval_steps_per_second": 0.555, "step": 3852 }, { "epoch": 7.0, "eval_gen_len": 18.5222, "eval_loss": 3.0167415142059326, "eval_rouge-1": 38.291, "eval_rouge-2": 20.6795, "eval_rouge-l": 37.3757, "eval_runtime": 97.7101, "eval_samples_per_second": 4.605, "eval_steps_per_second": 0.583, "step": 4494 }, { "epoch": 7.79, "learning_rate": 8.715112540192926e-05, "loss": 2.8376, "step": 5000 }, { "epoch": 8.0, "eval_gen_len": 18.0733, "eval_loss": 3.062363624572754, "eval_rouge-1": 39.3253, "eval_rouge-2": 21.9098, "eval_rouge-l": 38.5872, "eval_runtime": 96.2268, "eval_samples_per_second": 4.676, "eval_steps_per_second": 0.592, "step": 5136 }, { "epoch": 8.0, "step": 5136, "total_flos": 1.346091953939712e+16, "train_loss": 2.820291715247609, "train_runtime": 3245.0074, "train_samples_per_second": 79.091, "train_steps_per_second": 9.892 } ], "logging_steps": 5000, "max_steps": 32100, "num_train_epochs": 50, "save_steps": 500, "total_flos": 1.346091953939712e+16, "trial_name": null, "trial_params": null }