metadata

license: apache-2.0
base_model: t5-small
tags:
  - generated_from_trainer
model-index:
  - name: t5-small-squad-qg-v2
    results:
      - task:
          type: text2text-generation
        metrics:
          - name: BLEU
            type: BLEU
            value: 20
          - name: Rouge1
            type: Rouge1
            value: 47.69
          - name: Rouge2
            type: Rouge2
            value: 26.43
          - name: RougeL
            type: RougeL
            value: 44.15
          - name: RougeLSum
            type: RougeLSum
            value: 44.15
          - name: METEOR
            type: METEOR
            value: 45.84
          - name: BertScore
            type: BertScore
            value: 91.82
widget:
  - text: >-
      Generate a question whose answer is highlighted by <h> from the context
      delimited by the triple backticks 

      context:```During the 2011–12 season, he set the La Liga and European
      records for most goals scored in a single season, while establishing
      himself as Barcelona all-time top scorer. The following two seasons, Messi
      finished second for the Ballon d'Or behind Cristiano Ronaldo (his
      perceived career rival), before regaining his best form during the 2014–15
      campaign, becoming the all-time top scorer in La Liga and leading
      Barcelona to a historic second treble, after which he was awarded a fifth
      Ballon d'Or in 2015. Messi assumed captaincy of Barcelona in 2018, and won
      a record sixth Ballon d'Or in 2019. Out of contract, he signed for French
      club Paris Saint-Germain in August 2021, spending two seasons at the club
      and winning Ligue 1 twice. Messi joined American club  <h> Inter Miami <h>
      in July 2023, winning the Leagues Cup in August of that year.```
datasets:
  - rajpurkar/squad
language:
  - en
metrics:
  - bleu
  - rouge
  - meteor
  - bertscore
pipeline_tag: text2text-generation

t5-small-squad-qg-v2

This model is a fine-tuned version of t5-small on the SQuAD dataset. It achieves the following results on the evaluation set:

Loss: 1.6608
BLEU: 20.00
Rouge1: 47.69
Rouge2: 26.43
RougeL: 44.15
RougeLSum: 44.15
METEOR: 45.84
BertScore: 91.82

Model description

Intended uses & limitations

Define some useful functions for highlighting the answer in the paragraph and preparing the instruction prompt that will be fed to the model:

def highlight_answer(context, answer):
    context_splits = context.split(answer)
    
    text = ""
    for split in context_splits:
        text += split
        text += ' <h> '
        text += answer
        text += ' <h> '
        text += split
    
    return text

def prepare_instruction(answer_highlighted_context):
    instruction_prompt = f"""Generate a question whose answer is highlighted by <h> from the context delimited by the triple backticks.
    context:
    ```
    {answer_highlighted_context}
    ```
    """
    
    return instruction_prompt

Use the model as a Hugging Face Pipeline:

from transformers import pipeline

pipe = pipeline('text2text-generation', model='mohammedaly2222002/t5-small-squad-qg')

context = """During the 2011–12 season, he set the La Liga and European records\
for most goals scored in a single season, while establishing himself as Barcelona's\
all-time top scorer. The following two seasons, Messi finished second for the Ballon\
d'Or behind Cristiano Ronaldo (his perceived career rival), before regaining his best\
form during the 2014–15 campaign, becoming the all-time top scorer in La Liga and \
leading Barcelona to a historic second treble, after which he was awarded a fifth \
Ballon d'Or in 2015. Messi assumed captaincy of Barcelona in 2018, and won a record \
sixth Ballon d'Or in 2019. Out of contract, he signed for French club Paris Saint-Germain\
in August 2021, spending two seasons at the club and winning Ligue 1 twice. Messi \
joined American club Inter Miami in July 2023, winning the Leagues Cup in August of that year.
"""

answer_highlighted_context = highlight_answer(context=context, answer='Inter Miami')
prompt = prepare_instruction(answer_highlighted_context)

This will be the final prompt:

Generate a question whose answer is highlighted by <h> from the context delimited by the triple backticks
context:
```During the 2011–12 season, he set the La Liga and European records\
for most goals scored in a single season, while establishing himself as Barcelona's\
all-time top scorer. The following two seasons, Messi finished second for the Ballon\
d'Or behind Cristiano Ronaldo (his perceived career rival), before regaining his best\
form during the 2014–15 campaign, becoming the all-time top scorer in La Liga and \
leading Barcelona to a historic second treble, after which he was awarded a fifth \
Ballon d'Or in 2015. Messi assumed captaincy of Barcelona in 2018, and won a record\
 sixth Ballon d'Or in 2019. Out of contract, he signed for French club Paris Saint-Germain\
in August 2021, spending two seasons at the club and winning Ligue 1 twice. Messi \
joined American club  <h> Inter Miami <h> in July 2023, winning the Leagues Cup in August of that year.```

Use the loaded pipeline to generate questions their answer is Inter Miami:

outputs = pipe(prompt, num_return_sequences=3, num_beams=5, num_beam_groups=5, diversity_penalty=1.0)
for output in outputs:
    print(output['generated_text'])

Result:

1. What club did Messi join in the 2023 season?
2. What was Messi's name of the club that won the Leagues Cup on July 20?
3. What club did Messi join in the Leagues Cup in July 2023?

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-06
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 1000
num_epochs: 10
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
2.6867	0.73	500	1.9647
2.0737	1.46	1000	1.8141
1.9364	2.19	1500	1.7515
1.8745	2.92	2000	1.7215
1.8282	3.65	2500	1.7042
1.803	4.38	3000	1.6913
1.7797	5.11	3500	1.6796
1.7592	5.84	4000	1.6749
1.7435	6.57	4500	1.6697
1.7427	7.3	5000	1.6667
1.7245	8.04	5500	1.6614
1.7211	8.77	6000	1.6621
1.7137	9.5	6500	1.6608

Framework versions

Transformers 4.38.1
Pytorch 2.1.2
Datasets 2.13.1
Tokenizers 0.15.2