metadata
license: apache-2.0
base_model: t5-small
tags:
- generated_from_trainer
datasets:
- legal_bench
metrics:
- rouge
model-index:
- name: legalbench_summarizer
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: legal_bench
type: legal_bench
config: consumer_contracts_qa
split: test
args: consumer_contracts_qa
metrics:
- name: Rouge1
type: rouge
value: 0.0029
legalbench_summarizer
This model is a fine-tuned version of t5-small on the legal_bench dataset. It achieves the following results on the evaluation set:
- Loss: 10.6817
- Rouge1: 0.0029
- Rouge2: 0.0
- Rougel: 0.003
- Rougelsum: 0.003
- 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: 32
- eval_batch_size: 32
- 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 |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 1 | 10.8579 | 0.0015 | 0.0 | 0.0016 | 0.0016 | 19.0 |
| No log | 2.0 | 2 | 10.7719 | 0.0018 | 0.0 | 0.0019 | 0.0019 | 19.0 |
| No log | 3.0 | 3 | 10.7123 | 0.0033 | 0.0 | 0.0033 | 0.0033 | 19.0 |
| No log | 4.0 | 4 | 10.6817 | 0.0029 | 0.0 | 0.003 | 0.003 | 19.0 |
Framework versions
- Transformers 4.37.0
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.15.1