metadata
library_name: transformers
license: apache-2.0
base_model: t5-small
tags:
- generated_from_trainer
datasets:
- samsum
metrics:
- rouge
model-index:
- name: t5_samsum_model_sam
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: samsum
type: samsum
config: samsum
split: test
args: samsum
metrics:
- name: Rouge1
type: rouge
value: 0.3507
t5_samsum_model_sam
This model is a fine-tuned version of t5-small on the samsum dataset. It achieves the following results on the evaluation set:
- Loss: 2.1845
- Rouge1: 0.3507
- Rouge2: 0.1284
- Rougel: 0.2992
- Rougelsum: 0.2983
- Gen Len: 17.25
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
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 2.5776 | 1.0 | 41 | 2.3880 | 0.2569 | 0.0605 | 0.2123 | 0.2123 | 18.5915 |
| 2.4682 | 2.0 | 82 | 2.2464 | 0.3093 | 0.0885 | 0.2555 | 0.2556 | 17.9207 |
| 2.3727 | 3.0 | 123 | 2.1970 | 0.3494 | 0.126 | 0.2975 | 0.2969 | 17.2195 |
| 2.3833 | 4.0 | 164 | 2.1845 | 0.3507 | 0.1284 | 0.2992 | 0.2983 | 17.25 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1