abstractive_summarization/src/dapt_pretraining.py [222:234]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    parser.add_argument("-adam_epsilon", default=1e-8, type=float, help="Epsilon for Adam optimizer.")
    parser.add_argument('-recadam', default=False, action='store_true')
    parser.add_argument("-weight_decay", default=0.0, type=float, help="Weight decay if we apply some.")
    parser.add_argument("-anneal_w", type=float, default=1.0, help="Weight for the annealing function in RecAdam. Default 1.0.")
    parser.add_argument("-anneal_fun", type=str, default='sigmoid', choices=["sigmoid", "linear", 'constant'], help="the type of annealing function in RecAdam. Default sigmoid")
    parser.add_argument("-anneal_t0", type=int, default=1000, help="t0 for the annealing function in RecAdam.")
    parser.add_argument("-anneal_k", type=float, default=0.1, help="k for the annealing function in RecAdam.")
    parser.add_argument("-pretrain_cof", type=float, default=5000.0, help="Coefficient of the quadratic penalty in RecAdam. Default 5000.0.")
    parser.add_argument("-logging_Euclid_dist", action="store_true", help="Whether to log the Euclidean distance between the pretrained model and fine-tuning model")
    parser.add_argument("-max_steps", default=-1, type=int, help="If > 0: set total number of training steps to perform. Override num_train_epochs.")
    parser.add_argument("-model_type", type=str, default="layers")

    args = parser.parse_args()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



abstractive_summarization/src/sdpt_pretraining.py [113:124]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    parser.add_argument("-adam_epsilon", default=1e-8, type=float, help="Epsilon for Adam optimizer.")
    parser.add_argument('-recadam', default=False, action='store_true')
    parser.add_argument("-weight_decay", default=0.0, type=float, help="Weight decay if we apply some.")
    parser.add_argument("-anneal_w", type=float, default=1.0, help="Weight for the annealing function in RecAdam. Default 1.0.")
    parser.add_argument("-anneal_fun", type=str, default='sigmoid', choices=["sigmoid", "linear", 'constant'], help="the type of annealing function in RecAdam. Default sigmoid")
    parser.add_argument("-anneal_t0", type=int, default=1000, help="t0 for the annealing function in RecAdam.")
    parser.add_argument("-anneal_k", type=float, default=0.1, help="k for the annealing function in RecAdam.")
    parser.add_argument("-pretrain_cof", type=float, default=5000.0, help="Coefficient of the quadratic penalty in RecAdam. Default 5000.0.")
    parser.add_argument("-logging_Euclid_dist", action="store_true", help="Whether to log the Euclidean distance between the pretrained model and fine-tuning model")
    parser.add_argument("-max_steps", default=-1, type=int, help="If > 0: set total number of training steps to perform. Override num_train_epochs.")
    parser.add_argument("-model_type", type=str, default="layers")
    args = parser.parse_args()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -