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: []
flan-t5-large-stacked-samsum1024-WIP3
This model is a fine-tuned version of pszemraj/flan-t5-large-stacked-samsum1024-WIP2 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
More information needed
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