metadata
license: apache-2.0
base_model: t5-small
tags:
- generated_from_trainer
datasets:
- samsum
metrics:
- rouge
model-index:
- name: t5-small-t5-dialogue-summarizer
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: samsum
type: samsum
config: samsum
split: validation
args: samsum
metrics:
- name: Rouge1
type: rouge
value: 41.8545
t5-small-t5-dialogue-summarizer
This model is a fine-tuned version of t5-small on the samsum dataset. It achieves the following results on the evaluation set:
- Loss: 1.7739
- Rouge1: 41.8545
- Rouge2: 19.0397
- Rougel: 35.2065
- Rougelsum: 38.8278
- Gen Len: 16.6222
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
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- 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 | 460 | 1.7926 | 41.5391 | 18.4858 | 34.6806 | 38.3183 | 16.6663 |
| 1.9666 | 2.0 | 921 | 1.7810 | 41.5694 | 18.5639 | 34.9915 | 38.4652 | 16.5599 |
| 1.9457 | 3.0 | 1381 | 1.7785 | 42.0475 | 19.0086 | 35.2119 | 38.8236 | 16.6858 |
| 1.9241 | 4.0 | 1840 | 1.7739 | 41.8545 | 19.0397 | 35.2065 | 38.8278 | 16.6222 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0