metadata

license: apache-2.0
tags:
  - generated_from_trainer
  - summarization
metrics:
  - rouge
datasets:
  - stacked-summaries/stacked-samsum-1024
model-index:
  - name: flan-t5-large-stacked-samsum1024-WIP3
    results:
      - task:
          type: summarization
          name: Summarization
        dataset:
          name: samsum
          type: samsum
          config: samsum
          split: test
        metrics:
          - name: ROUGE-1
            type: rouge
            value: 47.6682
            verified: true
          - name: ROUGE-2
            type: rouge
            value: 23.3053
            verified: true
          - name: ROUGE-L
            type: rouge
            value: 39.7678
            verified: true
          - name: ROUGE-LSUM
            type: rouge
            value: 43.259
            verified: true
          - name: loss
            type: loss
            value: 2.372586965560913
            verified: true
          - name: gen_len
            type: gen_len
            value: 17.4237
            verified: true

flan-t5-large-stacked-samsum-1024

This model is a fine-tuned version of google/flan-t5-large on the stacked-summaries/stacked-samsum-1024 dataset.

It achieves the following results on the evaluation set:

Loss: 2.1311
Rouge1: 58.1114
Rouge2: 29.339
Rougel: 44.7611
Rougelsum: 54.2823
Gen Len: 122.364

Model description

More information needed

Intended uses & limitations

max input/output is 1024 tokens
this is mostly a test because samsum is not exactly the best dataset for general purpose summarization

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0006
train_batch_size: 4
eval_batch_size: 2
seed: 2760
distributed_type: multi-GPU
num_devices: 2
gradient_accumulation_steps: 32
total_train_batch_size: 256
total_eval_batch_size: 4
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.02
num_epochs: 2.0

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
0.1734	1.0	115	1.8751	57.9286	29.2743	44.7181	54.2295	122.123
0.1098	2.0	230	2.1311	58.1114	29.339	44.7611	54.2823	122.364

Framework versions

Transformers 4.26.0.dev0
Pytorch 1.13.0+cu117
Datasets 2.6.1
Tokenizers 0.13.1