PavanNeerudu's picture
Update README.md
e489eb9
metadata
language:
  - en
license: apache-2.0
datasets:
  - glue
metrics:
  - accuracy
model-index:
  - name: t5-base-finetuned-sst2
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE SST-2
          type: glue
          args: SST-2
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9323

T5-base-finetuned-sst2

This model is T5 fine-tuned on GLUE SST-2 dataset. It acheives the following results on the validation set

  • Accuracy: 0.9323

Model Details

T5 is an encoder-decoder model pre-trained on a multi-task mixture of unsupervised and supervised tasks and for which each task is converted into a text-to-text format.

Training procedure

Tokenization

Since, T5 is a text-to-text model, the labels of the dataset are converted as follows: For each example, a sentence as been formed as "sst2 sentence: " + sst2_sent and fed to the tokenizer to get the input_ids and attention_mask. For each label, label is choosen as "positive" if label is 1, else label is "negative" and tokenized to get input_ids and attention_mask . During training, these inputs_ids having pad token are replaced with -100 so that loss is not calculated for them. Then these input ids are given as labels, and above attention_mask of labels is given as decoder attention mask.

Training hyperparameters

The following hyperparameters were used during training: - learning_rate: 3e-4 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: epsilon=1e-08 - num_epochs: 2

Training results

Epoch Training Loss Validation Accuracy
1 0.1045 0.9323
2 0.0539 0.9243