metadata
library_name: transformers
license: apache-2.0
base_model: t5-small
tags:
- generated_from_trainer
datasets:
- big_patent
metrics:
- rouge
model-index:
- name: my_T5_summarization_model
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: big_patent
type: big_patent
config: f
split: validation
args: f
metrics:
- name: Rouge1
type: rouge
value: 0.2277
my_T5_summarization_model
This model is a fine-tuned version of t5-small on the big_patent dataset. It achieves the following results on the evaluation set:
- Loss: 1.9477
- Rouge1: 0.2277
- Rouge2: 0.1286
- Rougel: 0.1988
- Rougelsum: 0.1988
- Gen Len: 19.0
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 2.156 | 1.0 | 5348 | 2.0181 | 0.2264 | 0.1267 | 0.1971 | 0.1972 | 19.0 |
| 2.1095 | 2.0 | 10696 | 1.9737 | 0.227 | 0.1276 | 0.1977 | 0.1978 | 19.0 |
| 2.0867 | 3.0 | 16044 | 1.9545 | 0.2277 | 0.1285 | 0.1987 | 0.1988 | 19.0 |
| 2.0577 | 4.0 | 21392 | 1.9477 | 0.2277 | 0.1286 | 0.1988 | 0.1988 | 19.0 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.19.1