metadata

language:
  - it
tags:
  - summarization
datasets:
  - ARTeLab/ilpost
metrics:
  - rouge
base_model: gsarti/it5-base
model-index:
  - name: summarization_ilpost
    results:
      - task:
          type: summarization
          name: Summarization
        dataset:
          name: medical_questions_pairs
          type: medical_questions_pairs
          config: default
          split: train
        metrics:
          - type: rouge
            value: 12.5087
            name: ROUGE-1
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOTk1NzM4NjEyYjlkOWQ3Yzk0NjNiNDYzZjIwNDZkYWFlYzJlNTA4ZThiNjEzYWQzZWVjYzVmNTYyNjlhMjgzOCIsInZlcnNpb24iOjF9.v6mtEtzUqnUfSBwZu-vXDJmuVGvj4IvSgUFjdWy1RX9ShaC0TtNZJ20W4zjrEZ26Xmk7uqC51hK5ya6kx11WDQ
          - type: rouge
            value: 3.6796
            name: ROUGE-2
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMWQ4YWRmZGVjZTk5YTdjYzZhNzNkZDBmOTRmMzVmODY4OGU4MjI5OTdmZGQ3MTRjNDBmYTBkMTE0MzQ4ZDQ5YSIsInZlcnNpb24iOjF9.Ux7-ReB2i0MLurwxzzOmIi6dGUCUeZNYXgnGX4f8MTVJBMeMFMRFsG3Im1j0-DnpIxuvXETc8J6eZ5PR_5nIAg
          - type: rouge
            value: 11.0954
            name: ROUGE-L
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNjRkZTYyYjRhNTNlMThkZjI3ZmE3MmNlOTFiMmQ0MGRhMTE3ZWM5ODk1OWRkZThiYTFiNDg5MjE2ODVhM2QyNyIsInZlcnNpb24iOjF9.yucLivteb6CxBBMZ1gydBhiWPBzwL2Ga9OS37z0o0tuPSWHjbsZtoVTzrHuJcjH-kwnR_QNA1AWokSf9grs4BQ
          - type: rouge
            value: 11.5897
            name: ROUGE-LSUM
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZDI4ZmYxOWQzOTcyNGIyMWM2NGU4MzM0ZWI1MjRkN2ExNzFmNDFlNzI4ZTI4M2NkYzY5MmQ4MDgxZjhjMDExMyIsInZlcnNpb24iOjF9.riA7X5EfOrBirLWMyOYS5UWReNAm1sjrAPihNuW4lx0IzKdafZ3bUJrH1QNojae5p_XP8AyU8yygZ7TQgN2gBw
          - type: loss
            value: 3.0159499645233154
            name: loss
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNzhmYzJlMWYwYTM2OGFlNjQ2YjkxYWI1YzNkOTRjMjI0NGQ2ZTNhYjUzN2RhMDQxMjI1NWUyYjgwNTYzN2RkNiIsInZlcnNpb24iOjF9.I_CHEnSn61amBXNSOqBXSkGL09fvRv700bHyC41vNowaBUNtO5vOabRfhYi0IuPmsEI8eh_IEVrwNpbTgdtlAg
          - type: gen_len
            value: 18.9961
            name: gen_len
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOWU5NDBkZDMyNWJjN2NkYWEyNGZjOGY5MDQyOTVmN2I5MTVhMTk0N2I5YjIxZjI4YmY0MmRmZmU3YWIzMGRiYSIsInZlcnNpb24iOjF9.GC80tSpC8-wSuuzGc8wG9iDeSZ6CU1gdczoLiYEFdz-JfCrZa82UGr0EHXTzbaPKjb2Di1MyeH77hygu5BJpCQ

summarization_ilpost

This model is a fine-tuned version of gsarti/it5-base on IlPost dataset for Abstractive Summarization.

It achieves the following results:

Loss: 1.6020
Rouge1: 33.7802
Rouge2: 16.2953
Rougel: 27.4797
Rougelsum: 30.2273
Gen Len: 45.3175

Usage

from transformers import T5Tokenizer, T5ForConditionalGeneration
tokenizer = T5Tokenizer.from_pretrained("ARTeLab/it5-summarization-ilpost")
model = T5ForConditionalGeneration.from_pretrained("ARTeLab/it5-summarization-ilpost")

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 6
eval_batch_size: 6
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 4.0

Framework versions

Transformers 4.12.0.dev0
Pytorch 1.9.1+cu102
Datasets 1.12.1
Tokenizers 0.10.3