README.md

metadata

tags:
  - generated_from_trainer
datasets:
  - navjordj/SNL_summarization
model-index:
  - name: t5-large-snl-2
    results:
      - task:
          name: Sequence-to-sequence Language Modeling
          type: text2text-generation
        dataset:
          name: snl-summarization
          type: snl-summarization
        metrics:
          - name: Rouge1
            type: rouge
            value: 35.1506
inference:
  parameters:
    max_length: 160
    repetition_penalty: 1.2

t5-large-snl-2

This model is a fine-tuned version of navjordj/t5-large-snl on the navjordj/SNL_summarization dataset. It achieves the following results on the evaluation set:

• eval_loss: 1.8691
• eval_rouge1: 35.1506
• eval_rouge2: 16.0888
• eval_rougeL: 29.7007
• eval_rougeLsum: 32.4251
• eval_gen_len: 41.5629
• eval_runtime: 261.235
• eval_samples_per_second: 3.135
• eval_steps_per_second: 0.199
• step: 0

Model description

More information needed

Intended uses & limitations

More information needed

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: 16
• eval_batch_size: 16
• seed: 42
• distributed_type: multi-GPU
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20.0

Framework versions

• Transformers 4.27.0.dev0
• Pytorch 1.13.1
• Datasets 2.10.1
• Tokenizers 0.13.2